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

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

Neuron 3032 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: 0.1345. Min Range: -0.1345

Max Act: 0.1345. Min Act: -0.0002

Data Index: 1396865 (Python Code)

Max Activating Token Index: 446

Text #1

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1258. Min Act: -0.0002

Data Index: 1621834 (Python Code)

Max Activating Token Index: 235

Text #2

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1326. Min Act: -0.0002

Data Index: 1136534 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1310. Min Act: -0.0002

Data Index: 603003 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1278. Min Act: -0.0002

Data Index: 1377124 (Python Code)

Max Activating Token Index: 105

Text #5

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1266. Min Act: -0.0002

Data Index: 1289928 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1181. Min Act: -0.0002

Data Index: 472539 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1201. Min Act: -0.0002

Data Index: 1570491 (Python Code)

Max Activating Token Index: 162

Text #8

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1162. Min Act: -0.0002

Data Index: 485041 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1158. Min Act: -0.0002

Data Index: 787499 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1115. Min Act: -0.0002

Data Index: 182070 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1446819 (Python Code)

Max Activating Token Index: 530

Text #12

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1328080 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1129. Min Act: -0.0002

Data Index: 690893 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1108. Min Act: -0.0002

Data Index: 147597 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1063. Min Act: -0.0002

Data Index: 755617 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1066. Min Act: -0.0002

Data Index: 975850 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1092. Min Act: -0.0002

Data Index: 1430038 (Python Code)

Max Activating Token Index: 509

Text #18

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1048. Min Act: -0.0002

Data Index: 1132027 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1083. Min Act: -0.0002

Data Index: 812679 (C4 (Web Text))

Max Activating Token Index: 541