Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 506 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0280. Min Act: -0.0003

Data Index: 837014 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0263. Min Act: -0.0003

Data Index: 259015 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0250. Min Act: -0.0003

Data Index: 1201397 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0271. Min Act: -0.0003

Data Index: 473154 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0246. Min Act: -0.0003

Data Index: 1058046 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0237. Min Act: -0.0003

Data Index: 835136 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1295668 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1208258 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0242. Min Act: -0.0003

Data Index: 35517 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1241851 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1175763 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0234. Min Act: -0.0003

Data Index: 213233 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0233. Min Act: -0.0003

Data Index: 90638 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0242. Min Act: -0.0003

Data Index: 466869 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0239. Min Act: -0.0003

Data Index: 13697 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0233. Min Act: -0.0003

Data Index: 1093389 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0238. Min Act: -0.0003

Data Index: 1137438 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0223. Min Act: -0.0003

Data Index: 65318 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0230. Min Act: -0.0003

Data Index: 953801 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0226. Min Act: -0.0003

Data Index: 611546 (C4 (Web Text))

Max Activating Token Index: 504