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

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

Neuron 3409 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: 0.0227. Min Range: -0.0227

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1621044 (Python Code)

Max Activating Token Index: 72

Text #1

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0221. Min Act: -0.0003

Data Index: 1552239 (Python Code)

Max Activating Token Index: 1021

Text #2

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0215. Min Act: -0.0003

Data Index: 943403 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0219. Min Act: -0.0003

Data Index: 826222 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0207. Min Act: -0.0003

Data Index: 649102 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0201. Min Act: -0.0003

Data Index: 484051 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1204909 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0194. Min Act: -0.0003

Data Index: 783609 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0196. Min Act: -0.0003

Data Index: 961230 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0192. Min Act: -0.0003

Data Index: 956355 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1275071 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0190. Min Act: -0.0003

Data Index: 172718 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0186. Min Act: -0.0003

Data Index: 714303 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0183. Min Act: -0.0003

Data Index: 185290 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0181. Min Act: -0.0003

Data Index: 614998 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0182. Min Act: -0.0003

Data Index: 432539 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0172. Min Act: -0.0003

Data Index: 385211 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0181. Min Act: -0.0003

Data Index: 1622938 (Python Code)

Max Activating Token Index: 830

Text #18

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0176. Min Act: -0.0003

Data Index: 1173760 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0172. Min Act: -0.0003

Data Index: 570196 (C4 (Web Text))

Max Activating Token Index: 946