Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 317 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0354. Min Act: -0.0005

Data Index: 1285788 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0280. Min Act: -0.0005

Data Index: 1251069 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0234. Min Act: -0.0006

Data Index: 1055087 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0233. Min Act: -0.0006

Data Index: 687034 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0216. Min Act: -0.0006

Data Index: 684718 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0204. Min Act: -0.0006

Data Index: 769767 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0206. Min Act: -0.0006

Data Index: 1456144 (Python Code)

Max Activating Token Index: 553

Text #7

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0197. Min Act: -0.0005

Data Index: 1015719 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0191. Min Act: -0.0005

Data Index: 1159013 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0193. Min Act: -0.0006

Data Index: 1103526 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0193. Min Act: -0.0006

Data Index: 294186 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0187. Min Act: -0.0006

Data Index: 680426 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0187. Min Act: -0.0005

Data Index: 1534268 (Python Code)

Max Activating Token Index: 556

Text #13

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1294440 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0186. Min Act: -0.0006

Data Index: 979293 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0185. Min Act: -0.0006

Data Index: 296758 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0180. Min Act: -0.0005

Data Index: 67160 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0179. Min Act: -0.0006

Data Index: 57535 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0183. Min Act: -0.0005

Data Index: 1002644 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0187. Min Act: -0.0005

Data Index: 1040763 (C4 (Web Text))

Max Activating Token Index: 42