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

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

Neuron 625 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: 0.0223. Min Range: -0.0223

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1305300 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0205. Min Act: -0.0002

Data Index: 166451 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0145. Min Act: -0.0002

Data Index: 582317 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0188. Min Act: -0.0002

Data Index: 989981 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1501951 (Python Code)

Max Activating Token Index: 242

Text #5

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0176. Min Act: -0.0002

Data Index: 50701 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0149. Min Act: -0.0002

Data Index: 390095 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1026948 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0213. Min Act: -0.0002

Data Index: 209264 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0165. Min Act: -0.0002

Data Index: 646239 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0168. Min Act: -0.0002

Data Index: 989065 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0175. Min Act: -0.0002

Data Index: 491708 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0163. Min Act: -0.0002

Data Index: 1075286 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0162. Min Act: -0.0002

Data Index: 961647 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1011614 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0173. Min Act: -0.0002

Data Index: 596198 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0184. Min Act: -0.0002

Data Index: 902579 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0179. Min Act: -0.0002

Data Index: 390012 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0191. Min Act: -0.0002

Data Index: 999901 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0190. Min Act: -0.0002

Data Index: 451653 (C4 (Web Text))

Max Activating Token Index: 568