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

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

Neuron 5067 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1229656 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0243. Min Act: -0.0002

Data Index: 1266462 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0236. Min Act: -0.0002

Data Index: 622991 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0234. Min Act: -0.0002

Data Index: 586923 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0236. Min Act: -0.0002

Data Index: 873103 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0236. Min Act: -0.0002

Data Index: 884264 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0234. Min Act: -0.0002

Data Index: 120924 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1170567 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0227. Min Act: -0.0002

Data Index: 408935 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1328919 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0221. Min Act: -0.0002

Data Index: 11875 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1026921 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1596392 (Python Code)

Max Activating Token Index: 862

Text #13

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1276770 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0216. Min Act: -0.0002

Data Index: 310634 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0215. Min Act: -0.0002

Data Index: 83457 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0220. Min Act: -0.0002

Data Index: 572670 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0209. Min Act: -0.0002

Data Index: 685149 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0213. Min Act: -0.0002

Data Index: 435825 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0212. Min Act: -0.0002

Data Index: 439834 (C4 (Web Text))

Max Activating Token Index: 630