Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3268 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1507. Min Act: -0.0002

Data Index: 1264027 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1352. Min Act: -0.0002

Data Index: 1325901 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1114. Min Act: -0.0002

Data Index: 1191540 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1236. Min Act: -0.0002

Data Index: 235854 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1251. Min Act: -0.0002

Data Index: 1174023 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1224. Min Act: -0.0002

Data Index: 528473 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1112. Min Act: -0.0002

Data Index: 1352000 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1235. Min Act: -0.0002

Data Index: 764878 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1114. Min Act: -0.0001

Data Index: 67896 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1246. Min Act: -0.0001

Data Index: 1153661 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1103. Min Act: -0.0002

Data Index: 1335933 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1288. Min Act: -0.0002

Data Index: 545087 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1208. Min Act: -0.0002

Data Index: 1315434 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1199. Min Act: -0.0001

Data Index: 603527 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1074. Min Act: -0.0002

Data Index: 212130 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1038. Min Act: -0.0001

Data Index: 303265 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1144. Min Act: -0.0002

Data Index: 1265004 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1167. Min Act: -0.0002

Data Index: 1264058 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1129. Min Act: -0.0001

Data Index: 151424 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1166. Min Act: -0.0001

Data Index: 104390 (C4 (Web Text))

Max Activating Token Index: 80