Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 167 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1235. Min Act: -0.0003

Data Index: 873953 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1222. Min Act: -0.0003

Data Index: 50540 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1145. Min Act: -0.0004

Data Index: 606358 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1144. Min Act: -0.0003

Data Index: 359968 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1181. Min Act: -0.0003

Data Index: 410742 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1181. Min Act: -0.0003

Data Index: 1204340 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1222. Min Act: -0.0003

Data Index: 710324 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1148. Min Act: -0.0004

Data Index: 1067184 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1148. Min Act: -0.0003

Data Index: 1296240 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1042. Min Act: -0.0003

Data Index: 967218 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1186. Min Act: -0.0003

Data Index: 1334995 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1178. Min Act: -0.0003

Data Index: 498555 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1174. Min Act: -0.0003

Data Index: 912850 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1143. Min Act: -0.0003

Data Index: 636339 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1129. Min Act: -0.0003

Data Index: 13920 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1159. Min Act: -0.0003

Data Index: 1093450 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1119. Min Act: -0.0003

Data Index: 361782 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1089. Min Act: -0.0003

Data Index: 469139 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1081. Min Act: -0.0004

Data Index: 702495 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1036. Min Act: -0.0004

Data Index: 136983 (C4 (Web Text))

Max Activating Token Index: 1020