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

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

Neuron 2021 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1017795 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0291. Min Act: -0.0002

Data Index: 767433 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0253. Min Act: -0.0002

Data Index: 395866 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0254. Min Act: -0.0002

Data Index: 432839 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0230. Min Act: -0.0002

Data Index: 726310 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1108036 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0220. Min Act: -0.0002

Data Index: 611721 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1357103 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1169369 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0157. Min Act: -0.0002

Data Index: 748991 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0207. Min Act: -0.0002

Data Index: 21492 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0214. Min Act: -0.0002

Data Index: 481868 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1231423 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0210. Min Act: -0.0002

Data Index: 910953 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1038515 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0192. Min Act: -0.0002

Data Index: 931102 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1033347 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0201. Min Act: -0.0002

Data Index: 794681 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0212. Min Act: -0.0002

Data Index: 645184 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0198. Min Act: -0.0002

Data Index: 32132 (C4 (Web Text))

Max Activating Token Index: 478