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

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

Neuron 517 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1264. Min Act: -0.0005

Data Index: 587723 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1068. Min Act: -0.0005

Data Index: 886804 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1103. Min Act: -0.0005

Data Index: 424639 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1063. Min Act: -0.0005

Data Index: 637764 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1042. Min Act: -0.0005

Data Index: 363571 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1121. Min Act: -0.0005

Data Index: 1322582 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1034. Min Act: -0.0005

Data Index: 337010 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1028. Min Act: -0.0005

Data Index: 1001201 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1058. Min Act: -0.0005

Data Index: 329465 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1090. Min Act: -0.0005

Data Index: 786391 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1047. Min Act: -0.0005

Data Index: 113242 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1049. Min Act: -0.0005

Data Index: 180962 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1067. Min Act: -0.0005

Data Index: 774749 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1023. Min Act: -0.0005

Data Index: 318859 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1011. Min Act: -0.0005

Data Index: 572590 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0977. Min Act: -0.0005

Data Index: 364458 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1007. Min Act: -0.0005

Data Index: 606557 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0961. Min Act: -0.0005

Data Index: 919517 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0969. Min Act: -0.0005

Data Index: 357923 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1000. Min Act: -0.0005

Data Index: 1100381 (C4 (Web Text))

Max Activating Token Index: 481