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

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

Neuron 4326 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: 0.1376. Min Range: -0.1376

Max Act: 0.1366. Min Act: -0.0002

Data Index: 797478 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1376. Min Act: -0.0002

Data Index: 281518 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1315. Min Act: -0.0002

Data Index: 315724 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1304. Min Act: -0.0002

Data Index: 1105018 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1293. Min Act: -0.0002

Data Index: 299496 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1267. Min Act: -0.0002

Data Index: 146244 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1304. Min Act: -0.0002

Data Index: 180793 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1239. Min Act: -0.0002

Data Index: 958902 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1149. Min Act: -0.0002

Data Index: 1072413 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1189. Min Act: -0.0002

Data Index: 121022 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1188. Min Act: -0.0002

Data Index: 401839 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1159. Min Act: -0.0002

Data Index: 980452 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1146. Min Act: -0.0002

Data Index: 962973 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1086. Min Act: -0.0002

Data Index: 1165317 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1163. Min Act: -0.0002

Data Index: 412029 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1158. Min Act: -0.0002

Data Index: 593682 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1112. Min Act: -0.0002

Data Index: 561212 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1147. Min Act: -0.0002

Data Index: 1346834 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1107. Min Act: -0.0002

Data Index: 952877 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1100. Min Act: -0.0002

Data Index: 47975 (C4 (Web Text))

Max Activating Token Index: 482