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

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

Neuron 3453 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0192. Min Act: -0.0003

Data Index: 612388 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0177. Min Act: -0.0002

Data Index: 671288 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0169. Min Act: -0.0003

Data Index: 547486 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1287164 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1026136 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0191. Min Act: -0.0003

Data Index: 1070075 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1096601 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0181. Min Act: -0.0003

Data Index: 625949 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0169. Min Act: -0.0003

Data Index: 383698 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0173. Min Act: -0.0003

Data Index: 385000 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0163. Min Act: -0.0002

Data Index: 826805 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0154. Min Act: -0.0003

Data Index: 14917 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0144. Min Act: -0.0003

Data Index: 230168 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0151. Min Act: -0.0003

Data Index: 1038336 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0164. Min Act: -0.0003

Data Index: 329462 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0146. Min Act: -0.0003

Data Index: 1064770 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0156. Min Act: -0.0003

Data Index: 10017 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0154. Min Act: -0.0002

Data Index: 108934 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1138320 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0143. Min Act: -0.0003

Data Index: 429567 (C4 (Web Text))

Max Activating Token Index: 612