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

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

Neuron 1067 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1233. Min Act: -0.0000

Data Index: 812482 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1134. Min Act: -0.0000

Data Index: 873254 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1087. Min Act: -0.0000

Data Index: 1328853 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1034. Min Act: -0.0000

Data Index: 686882 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1054. Min Act: -0.0000

Data Index: 726767 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0982. Min Act: -0.0000

Data Index: 625863 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0864. Min Act: -0.0000

Data Index: 765051 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0800. Min Act: -0.0000

Data Index: 666855 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0828. Min Act: -0.0000

Data Index: 228272 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0849. Min Act: -0.0000

Data Index: 133236 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0770. Min Act: -0.0000

Data Index: 629670 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0796. Min Act: -0.0000

Data Index: 74490 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0833. Min Act: -0.0000

Data Index: 88118 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0733. Min Act: -0.0000

Data Index: 454729 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0729. Min Act: -0.0000

Data Index: 849933 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0779. Min Act: -0.0000

Data Index: 1125631 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0731. Min Act: -0.0000

Data Index: 1326442 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0688. Min Act: -0.0000

Data Index: 1136000 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0710. Min Act: -0.0000

Data Index: 87131 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0677. Min Act: -0.0000

Data Index: 903339 (C4 (Web Text))

Max Activating Token Index: 443