Anecdotally, social connections made in university have life-long impact. Yet knowledge of social networks formed in college remains episodic, due in large part to the difficulty and expense involved in collecting a suitable dataset for comprehensive analysis. To advance and systematize insight into college social networks, we describe a dataset of the largest online social network platform used by college students in the United States. We combine de-identified and aggregated Facebook data with College Scorecard data, campus-level information provided by U.S. Department of Education, to produce a dataset covering the 2008-2015 entry year cohorts for 1,159 U.S. colleges and universities, spanning 7.6 million students. To perform the difficult task of comparing these networks of different sizes we develop a new methodology. We compute features over sampled ego-graphs, train binary classifiers for every pair of graphs, and operationalize distance between graphs as predictive accuracy. Social networks of different year cohorts at the same school are structurally more similar to one another than to cohorts at other schools. Networks from similar schools have similar structures, with the public/private and graduation rate dimensions being the most distinguishable. We also relate school types to specific outcomes. For example, students at private schools have larger networks that are more clustered and with higher homophily by year. Our findings may help illuminate the role that colleges play in shaping social networks which partly persist throughout people's lives.