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

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

Neuron 1500 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: 0.0460. Min Range: -0.0460

Max Act: 0.0460. Min Act: -0.0003

Data Index: 1336869 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1212933 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0309. Min Act: -0.0002

Data Index: 885606 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0311. Min Act: -0.0002

Data Index: 885973 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1031989 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0258. Min Act: -0.0003

Data Index: 391984 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0252. Min Act: -0.0003

Data Index: 579069 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0251. Min Act: -0.0002

Data Index: 156282 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0240. Min Act: -0.0003

Data Index: 109566 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0253. Min Act: -0.0002

Data Index: 702048 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0252. Min Act: -0.0002

Data Index: 335080 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0247. Min Act: -0.0003

Data Index: 675110 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0242. Min Act: -0.0003

Data Index: 1198825 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0231. Min Act: -0.0003

Data Index: 297121 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0229. Min Act: -0.0002

Data Index: 209877 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1270969 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0226. Min Act: -0.0003

Data Index: 472920 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1071714 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0219. Min Act: -0.0003

Data Index: 461487 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0223. Min Act: -0.0003

Data Index: 806338 (C4 (Web Text))

Max Activating Token Index: 58