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

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

Neuron 4784 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0248. Min Act: -0.0002

Data Index: 750416 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0280. Min Act: -0.0002

Data Index: 246933 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0251. Min Act: -0.0002

Data Index: 576425 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0229. Min Act: -0.0002

Data Index: 799488 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1031041 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0246. Min Act: -0.0002

Data Index: 168597 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0239. Min Act: -0.0002

Data Index: 1230288 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1002331 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0226. Min Act: -0.0002

Data Index: 79860 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0220. Min Act: -0.0002

Data Index: 281900 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1228688 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1069749 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1107656 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0228. Min Act: -0.0002

Data Index: 84349 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1274443 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0209. Min Act: -0.0002

Data Index: 172322 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1117035 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1145950 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1048768 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0227. Min Act: -0.0002

Data Index: 747218 (C4 (Web Text))

Max Activating Token Index: 840