Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3648 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1535. Min Act: -0.0002

Data Index: 205259 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1323. Min Act: -0.0002

Data Index: 200074 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1318. Min Act: -0.0002

Data Index: 896976 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1229. Min Act: -0.0002

Data Index: 1026975 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1264. Min Act: -0.0002

Data Index: 1117193 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1261. Min Act: -0.0002

Data Index: 1315224 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1255. Min Act: -0.0002

Data Index: 27466 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1240. Min Act: -0.0002

Data Index: 355371 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1237. Min Act: -0.0002

Data Index: 1015720 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1265. Min Act: -0.0002

Data Index: 1028506 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1205. Min Act: -0.0002

Data Index: 562206 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1208. Min Act: -0.0002

Data Index: 739790 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1191. Min Act: -0.0002

Data Index: 1224968 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1166. Min Act: -0.0002

Data Index: 866497 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1159. Min Act: -0.0002

Data Index: 1308905 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1161. Min Act: -0.0002

Data Index: 777218 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1129. Min Act: -0.0002

Data Index: 1019720 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1168. Min Act: -0.0002

Data Index: 239058 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1080. Min Act: -0.0002

Data Index: 1238351 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1144. Min Act: -0.0002

Data Index: 340962 (C4 (Web Text))

Max Activating Token Index: 461