Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1493 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1173. Min Act: -0.0000

Data Index: 405429 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1190. Min Act: -0.0000

Data Index: 973241 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1150. Min Act: -0.0000

Data Index: 483522 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1292. Min Act: -0.0000

Data Index: 491167 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1214. Min Act: -0.0000

Data Index: 859823 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1235. Min Act: -0.0000

Data Index: 780330 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1122. Min Act: -0.0000

Data Index: 32509 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1006. Min Act: -0.0000

Data Index: 726779 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1077. Min Act: -0.0000

Data Index: 815993 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1068. Min Act: -0.0000

Data Index: 755598 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1031. Min Act: -0.0000

Data Index: 744345 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1063. Min Act: -0.0000

Data Index: 498732 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1041. Min Act: -0.0000

Data Index: 1164394 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1070. Min Act: -0.0000

Data Index: 324811 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1032. Min Act: -0.0000

Data Index: 720019 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1063. Min Act: -0.0000

Data Index: 505103 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1028015 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1070. Min Act: -0.0000

Data Index: 986041 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1232987 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1174. Min Act: -0.0000

Data Index: 1166460 (C4 (Web Text))

Max Activating Token Index: 663