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

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

Neuron 1499 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: 0.1346. Min Range: -0.1346

Max Act: 0.1346. Min Act: -0.0003

Data Index: 898953 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1300. Min Act: -0.0003

Data Index: 344006 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1234. Min Act: -0.0004

Data Index: 401892 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1205. Min Act: -0.0003

Data Index: 1353323 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1213. Min Act: -0.0003

Data Index: 904760 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1152. Min Act: -0.0003

Data Index: 927829 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1193. Min Act: -0.0003

Data Index: 270068 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1201. Min Act: -0.0003

Data Index: 1275722 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1210. Min Act: -0.0003

Data Index: 702045 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1185. Min Act: -0.0003

Data Index: 370189 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1187. Min Act: -0.0003

Data Index: 325307 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1156. Min Act: -0.0004

Data Index: 301165 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1180. Min Act: -0.0003

Data Index: 1317449 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1124. Min Act: -0.0002

Data Index: 966975 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1173. Min Act: -0.0003

Data Index: 263160 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1102. Min Act: -0.0002

Data Index: 1126808 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1135. Min Act: -0.0003

Data Index: 373954 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1148. Min Act: -0.0003

Data Index: 1030074 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1114. Min Act: -0.0003

Data Index: 665995 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1145. Min Act: -0.0003

Data Index: 413511 (C4 (Web Text))

Max Activating Token Index: 16