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

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

Neuron 3192 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2945. Min Range: -3.2945

Max Act: 3.2945. Min Act: -0.0000

Data Index: 830409 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 3.2945. Min Range: -3.2945

Max Act: 3.0905. Min Act: -0.0000

Data Index: 854488 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 3.2945. Min Range: -3.2945

Max Act: 2.8121. Min Act: -0.0000

Data Index: 195518 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 3.2945. Min Range: -3.2945

Max Act: 2.8019. Min Act: -0.0000

Data Index: 864681 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 3.2945. Min Range: -3.2945

Max Act: 2.7571. Min Act: -0.0000

Data Index: 1119489 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 3.2945. Min Range: -3.2945

Max Act: 2.7194. Min Act: -0.0000

Data Index: 633320 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 3.2945. Min Range: -3.2945

Max Act: 2.6928. Min Act: -0.0000

Data Index: 1042121 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 3.2945. Min Range: -3.2945

Max Act: 2.5502. Min Act: -0.0000

Data Index: 999331 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 3.2945. Min Range: -3.2945

Max Act: 2.5354. Min Act: -0.0000

Data Index: 1270970 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 3.2945. Min Range: -3.2945

Max Act: 2.5046. Min Act: -0.0000

Data Index: 737645 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 3.2945. Min Range: -3.2945

Max Act: 2.6167. Min Act: -0.0000

Data Index: 259611 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 3.2945. Min Range: -3.2945

Max Act: 2.5831. Min Act: -0.0000

Data Index: 1033145 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 3.2945. Min Range: -3.2945

Max Act: 2.5584. Min Act: -0.0000

Data Index: 353883 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 3.2945. Min Range: -3.2945

Max Act: 2.5465. Min Act: -0.0000

Data Index: 1336009 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 3.2945. Min Range: -3.2945

Max Act: 2.5199. Min Act: -0.0000

Data Index: 199633 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 3.2945. Min Range: -3.2945

Max Act: 2.3389. Min Act: -0.0000

Data Index: 804129 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 3.2945. Min Range: -3.2945

Max Act: 2.3264. Min Act: -0.0000

Data Index: 636289 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 3.2945. Min Range: -3.2945

Max Act: 2.4699. Min Act: -0.0000

Data Index: 1292524 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 3.2945. Min Range: -3.2945

Max Act: 2.5621. Min Act: -0.0000

Data Index: 1200398 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 3.2945. Min Range: -3.2945

Max Act: 2.2735. Min Act: -0.0000

Data Index: 590378 (C4 (Web Text))

Max Activating Token Index: 343