Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 175 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1346. Min Act: -0.0002

Data Index: 604288 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1283. Min Act: -0.0002

Data Index: 157975 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1229. Min Act: -0.0002

Data Index: 1190387 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1225. Min Act: -0.0002

Data Index: 910055 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1195. Min Act: -0.0002

Data Index: 624699 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1216. Min Act: -0.0002

Data Index: 611603 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1245. Min Act: -0.0002

Data Index: 284576 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1231. Min Act: -0.0002

Data Index: 94236 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1193. Min Act: -0.0002

Data Index: 339415 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1212. Min Act: -0.0002

Data Index: 588259 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1246. Min Act: -0.0002

Data Index: 988999 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1213. Min Act: -0.0002

Data Index: 303197 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1211. Min Act: -0.0002

Data Index: 522289 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1166. Min Act: -0.0002

Data Index: 255241 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1236. Min Act: -0.0002

Data Index: 1236810 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1165. Min Act: -0.0002

Data Index: 1078426 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1145. Min Act: -0.0002

Data Index: 706077 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1114. Min Act: -0.0002

Data Index: 933300 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1175. Min Act: -0.0002

Data Index: 1173050 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1153. Min Act: -0.0002

Data Index: 349677 (C4 (Web Text))

Max Activating Token Index: 204