Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1035 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1313. Min Act: -0.0001

Data Index: 805105 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1257. Min Act: -0.0001

Data Index: 1025873 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1264. Min Act: -0.0001

Data Index: 1246204 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1124. Min Act: -0.0001

Data Index: 30276 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1131. Min Act: -0.0001

Data Index: 231638 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1167. Min Act: -0.0001

Data Index: 178438 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1232. Min Act: -0.0001

Data Index: 1316965 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1124. Min Act: -0.0001

Data Index: 758467 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1079. Min Act: -0.0001

Data Index: 601436 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1111. Min Act: -0.0001

Data Index: 395424 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1041. Min Act: -0.0001

Data Index: 529456 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1137. Min Act: -0.0001

Data Index: 552834 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1100. Min Act: -0.0001

Data Index: 1229051 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1095. Min Act: -0.0001

Data Index: 208129 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1084. Min Act: -0.0001

Data Index: 675121 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1190296 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1128. Min Act: -0.0001

Data Index: 1031367 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1107. Min Act: -0.0001

Data Index: 975396 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1072. Min Act: -0.0001

Data Index: 1053276 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1061. Min Act: -0.0001

Data Index: 762267 (C4 (Web Text))

Max Activating Token Index: 478