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

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

Neuron 1735 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0211. Min Act: -0.0006

Data Index: 380414 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0209. Min Act: -0.0006

Data Index: 292777 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0207. Min Act: -0.0006

Data Index: 960673 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0206. Min Act: -0.0006

Data Index: 118112 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0198. Min Act: -0.0006

Data Index: 7346 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0200. Min Act: -0.0006

Data Index: 54001 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0197. Min Act: -0.0006

Data Index: 231330 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0195. Min Act: -0.0006

Data Index: 491382 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0194. Min Act: -0.0006

Data Index: 490566 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0194. Min Act: -0.0006

Data Index: 806686 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0194. Min Act: -0.0006

Data Index: 1083625 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0198. Min Act: -0.0006

Data Index: 1294230 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0193. Min Act: -0.0006

Data Index: 387722 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0192. Min Act: -0.0006

Data Index: 510530 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0191. Min Act: -0.0006

Data Index: 16707 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0189. Min Act: -0.0006

Data Index: 376027 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0190. Min Act: -0.0006

Data Index: 942825 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0188. Min Act: -0.0006

Data Index: 242837 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0195. Min Act: -0.0006

Data Index: 1328650 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0192. Min Act: -0.0006

Data Index: 402099 (C4 (Web Text))

Max Activating Token Index: 474