Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2060 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0324. Min Act: -0.0003

Data Index: 300918 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0270. Min Act: -0.0003

Data Index: 449797 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0246. Min Act: -0.0003

Data Index: 600626 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0224. Min Act: -0.0003

Data Index: 1280082 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0233. Min Act: -0.0003

Data Index: 599909 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0203. Min Act: -0.0003

Data Index: 541027 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0213. Min Act: -0.0003

Data Index: 472477 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0203. Min Act: -0.0003

Data Index: 1220716 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0211. Min Act: -0.0003

Data Index: 20059 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0179. Min Act: -0.0003

Data Index: 143626 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0205. Min Act: -0.0003

Data Index: 885408 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0211. Min Act: -0.0003

Data Index: 1261245 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0190. Min Act: -0.0003

Data Index: 1164527 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0202. Min Act: -0.0003

Data Index: 246548 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0174. Min Act: -0.0003

Data Index: 121299 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0181. Min Act: -0.0003

Data Index: 472988 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1146625 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0187. Min Act: -0.0003

Data Index: 796826 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0177. Min Act: -0.0003

Data Index: 1224748 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0178. Min Act: -0.0003

Data Index: 1074400 (C4 (Web Text))

Max Activating Token Index: 119