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

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

Neuron 108 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: 0.0216. Min Range: -0.0216

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1152476 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0206. Min Act: -0.0003

Data Index: 421893 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0201. Min Act: -0.0003

Data Index: 219890 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0204. Min Act: -0.0002

Data Index: 944912 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0196. Min Act: -0.0003

Data Index: 200193 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0203. Min Act: -0.0002

Data Index: 272233 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0190. Min Act: -0.0003

Data Index: 819447 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0180. Min Act: -0.0003

Data Index: 539999 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1318622 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0183. Min Act: -0.0002

Data Index: 864604 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0179. Min Act: -0.0003

Data Index: 498190 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0179. Min Act: -0.0002

Data Index: 983795 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0187. Min Act: -0.0002

Data Index: 956887 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0174. Min Act: -0.0003

Data Index: 920052 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1048432 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0168. Min Act: -0.0003

Data Index: 258493 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1435670 (Python Code)

Max Activating Token Index: 854

Text #17

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0164. Min Act: -0.0003

Data Index: 511793 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0164. Min Act: -0.0003

Data Index: 547990 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0161. Min Act: -0.0003

Data Index: 894718 (C4 (Web Text))

Max Activating Token Index: 978