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

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

Neuron 1650 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0282. Min Act: -0.0006

Data Index: 216657 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0290. Min Act: -0.0006

Data Index: 203252 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0274. Min Act: -0.0006

Data Index: 443427 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0271. Min Act: -0.0006

Data Index: 1006571 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0268. Min Act: -0.0006

Data Index: 1245865 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0252. Min Act: -0.0006

Data Index: 371463 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0246. Min Act: -0.0006

Data Index: 762429 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0243. Min Act: -0.0006

Data Index: 1179144 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0230. Min Act: -0.0006

Data Index: 396695 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0243. Min Act: -0.0006

Data Index: 22276 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0227. Min Act: -0.0006

Data Index: 710417 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0235. Min Act: -0.0006

Data Index: 174005 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0235. Min Act: -0.0006

Data Index: 774531 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0235. Min Act: -0.0006

Data Index: 269995 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0233. Min Act: -0.0006

Data Index: 203295 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0232. Min Act: -0.0006

Data Index: 757243 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0236. Min Act: -0.0006

Data Index: 236875 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0230. Min Act: -0.0006

Data Index: 531446 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0222. Min Act: -0.0006

Data Index: 332458 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0237. Min Act: -0.0006

Data Index: 220343 (C4 (Web Text))

Max Activating Token Index: 163