Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2513 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0213. Min Act: -0.0004

Data Index: 1390824 (Python Code)

Max Activating Token Index: 556

Text #1

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0239. Min Act: -0.0004

Data Index: 1057304 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0195. Min Act: -0.0004

Data Index: 507326 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0185. Min Act: -0.0004

Data Index: 974843 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0193. Min Act: -0.0004

Data Index: 983318 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0191. Min Act: -0.0004

Data Index: 298203 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0184. Min Act: -0.0004

Data Index: 381487 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0207. Min Act: -0.0004

Data Index: 1076827 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0183. Min Act: -0.0004

Data Index: 714109 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0196. Min Act: -0.0004

Data Index: 1334832 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0171. Min Act: -0.0004

Data Index: 164312 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0217. Min Act: -0.0004

Data Index: 150770 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0176. Min Act: -0.0004

Data Index: 371812 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0175. Min Act: -0.0004

Data Index: 1057617 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0186. Min Act: -0.0004

Data Index: 49088 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0167. Min Act: -0.0004

Data Index: 622802 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0185. Min Act: -0.0004

Data Index: 1390602 (Python Code)

Max Activating Token Index: 962

Text #17

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0184. Min Act: -0.0004

Data Index: 937366 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0188. Min Act: -0.0004

Data Index: 189297 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0200. Min Act: -0.0004

Data Index: 981823 (C4 (Web Text))

Max Activating Token Index: 895