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

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

Neuron 57 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: 0.1418. Min Range: -0.1418

Max Act: 0.1418. Min Act: -0.0002

Data Index: 433771 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1288. Min Act: -0.0002

Data Index: 422362 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1216. Min Act: -0.0002

Data Index: 1194095 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1187. Min Act: -0.0002

Data Index: 1258576 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1199. Min Act: -0.0002

Data Index: 475406 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1137. Min Act: -0.0002

Data Index: 1267234 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1266. Min Act: -0.0002

Data Index: 491801 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1145. Min Act: -0.0002

Data Index: 306705 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1218. Min Act: -0.0002

Data Index: 446418 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1141. Min Act: -0.0002

Data Index: 782011 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1151. Min Act: -0.0002

Data Index: 441995 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1087. Min Act: -0.0002

Data Index: 401411 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1163. Min Act: -0.0002

Data Index: 189522 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1102. Min Act: -0.0002

Data Index: 1096901 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1123. Min Act: -0.0002

Data Index: 699937 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1094. Min Act: -0.0002

Data Index: 771859 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1114. Min Act: -0.0002

Data Index: 279717 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1139. Min Act: -0.0002

Data Index: 117874 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1120. Min Act: -0.0002

Data Index: 207467 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1057. Min Act: -0.0002

Data Index: 702582 (C4 (Web Text))

Max Activating Token Index: 871