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

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

Neuron 4284 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1293. Min Act: -0.0001

Data Index: 667368 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1178. Min Act: -0.0001

Data Index: 829159 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1226. Min Act: -0.0001

Data Index: 860396 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1165. Min Act: -0.0002

Data Index: 574206 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1125. Min Act: -0.0001

Data Index: 752315 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1158. Min Act: -0.0001

Data Index: 1227733 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1185. Min Act: -0.0001

Data Index: 729452 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1057. Min Act: -0.0001

Data Index: 878231 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1178. Min Act: -0.0001

Data Index: 1088463 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1074. Min Act: -0.0001

Data Index: 16303 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1076. Min Act: -0.0001

Data Index: 689399 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1027. Min Act: -0.0001

Data Index: 587966 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1106. Min Act: -0.0001

Data Index: 659952 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0998. Min Act: -0.0001

Data Index: 936726 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1086. Min Act: -0.0001

Data Index: 86575 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1041. Min Act: -0.0001

Data Index: 179185 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1070. Min Act: -0.0001

Data Index: 533078 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1044. Min Act: -0.0001

Data Index: 232102 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1089. Min Act: -0.0001

Data Index: 983728 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1077. Min Act: -0.0001

Data Index: 1154635 (C4 (Web Text))

Max Activating Token Index: 482