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

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

Neuron 22 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0277. Min Act: -0.0001

Data Index: 38323 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0230. Min Act: -0.0001

Data Index: 987033 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0239. Min Act: -0.0001

Data Index: 254902 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0239. Min Act: -0.0001

Data Index: 1100161 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0210. Min Act: -0.0001

Data Index: 217945 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0222. Min Act: -0.0001

Data Index: 1120237 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0212. Min Act: -0.0001

Data Index: 1301092 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0205. Min Act: -0.0001

Data Index: 56256 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0206. Min Act: -0.0001

Data Index: 831697 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0196. Min Act: -0.0001

Data Index: 1534049 (Python Code)

Max Activating Token Index: 117

Text #10

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0196. Min Act: -0.0001

Data Index: 785592 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0177. Min Act: -0.0001

Data Index: 1047667 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0195. Min Act: -0.0001

Data Index: 328694 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0196. Min Act: -0.0001

Data Index: 1239138 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0190. Min Act: -0.0001

Data Index: 3028 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0202. Min Act: -0.0001

Data Index: 469920 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0186. Min Act: -0.0001

Data Index: 81187 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0185. Min Act: -0.0001

Data Index: 999738 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0201. Min Act: -0.0001

Data Index: 275405 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0189. Min Act: -0.0001

Data Index: 794087 (C4 (Web Text))

Max Activating Token Index: 380