Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4300 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0308. Min Act: -0.0003

Data Index: 11491 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0293. Min Act: -0.0003

Data Index: 867760 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0289. Min Act: -0.0002

Data Index: 860661 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0273. Min Act: -0.0003

Data Index: 656799 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0273. Min Act: -0.0003

Data Index: 316793 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0272. Min Act: -0.0003

Data Index: 770285 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0263. Min Act: -0.0003

Data Index: 794193 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0269. Min Act: -0.0003

Data Index: 762166 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0257. Min Act: -0.0003

Data Index: 1245377 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1021927 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1253267 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0257. Min Act: -0.0003

Data Index: 287634 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0252. Min Act: -0.0003

Data Index: 403413 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0254. Min Act: -0.0003

Data Index: 614743 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0246. Min Act: -0.0002

Data Index: 793905 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0256. Min Act: -0.0003

Data Index: 60848 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0247. Min Act: -0.0003

Data Index: 11807 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0257. Min Act: -0.0003

Data Index: 1066560 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1199525 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0236. Min Act: -0.0003

Data Index: 108146 (C4 (Web Text))

Max Activating Token Index: 617