Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1350 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1383. Min Act: -0.0002

Data Index: 648985 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1332. Min Act: -0.0002

Data Index: 948745 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1363. Min Act: -0.0002

Data Index: 750730 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1244. Min Act: -0.0002

Data Index: 1220677 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1264. Min Act: -0.0002

Data Index: 477857 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1256. Min Act: -0.0002

Data Index: 1258268 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1179. Min Act: -0.0002

Data Index: 1353899 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1262. Min Act: -0.0002

Data Index: 972006 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1174. Min Act: -0.0002

Data Index: 283014 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1171. Min Act: -0.0001

Data Index: 1348239 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1170. Min Act: -0.0002

Data Index: 671872 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1176. Min Act: -0.0002

Data Index: 42994 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1158. Min Act: -0.0002

Data Index: 1154352 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1205. Min Act: -0.0002

Data Index: 1197537 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1123. Min Act: -0.0002

Data Index: 297404 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1071. Min Act: -0.0002

Data Index: 807483 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1148. Min Act: -0.0002

Data Index: 1049814 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1147. Min Act: -0.0002

Data Index: 530286 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1129. Min Act: -0.0002

Data Index: 1237054 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1091. Min Act: -0.0002

Data Index: 1105239 (C4 (Web Text))

Max Activating Token Index: 207