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

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

Neuron 3416 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: 0.1588. Min Range: -0.1588

Max Act: 0.1588. Min Act: -0.0003

Data Index: 497841 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1477. Min Act: -0.0003

Data Index: 1273658 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1422. Min Act: -0.0003

Data Index: 822446 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1422. Min Act: -0.0003

Data Index: 549456 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1373. Min Act: -0.0003

Data Index: 1295751 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1308. Min Act: -0.0002

Data Index: 317555 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1312. Min Act: -0.0003

Data Index: 1134070 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1345. Min Act: -0.0003

Data Index: 309899 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1309. Min Act: -0.0003

Data Index: 1179597 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1261. Min Act: -0.0003

Data Index: 1229876 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1237. Min Act: -0.0003

Data Index: 820840 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1229. Min Act: -0.0003

Data Index: 21110 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1224. Min Act: -0.0003

Data Index: 383814 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1221. Min Act: -0.0003

Data Index: 1019230 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1208. Min Act: -0.0003

Data Index: 144 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1206. Min Act: -0.0003

Data Index: 955196 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1148. Min Act: -0.0003

Data Index: 161868 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1152. Min Act: -0.0003

Data Index: 1169756 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1195. Min Act: -0.0003

Data Index: 1144515 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1182. Min Act: -0.0003

Data Index: 426086 (C4 (Web Text))

Max Activating Token Index: 470