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

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

Neuron 1109 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4560. Min Range: -1.4560

Max Act: 1.4251. Min Act: -0.0002

Data Index: 1038510 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 1.4560. Min Range: -1.4560

Max Act: 1.3802. Min Act: -0.0002

Data Index: 989798 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 1.4560. Min Range: -1.4560

Max Act: 1.4257. Min Act: -0.0002

Data Index: 649285 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 1.4560. Min Range: -1.4560

Max Act: 1.4560. Min Act: -0.0002

Data Index: 636041 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 1.4560. Min Range: -1.4560

Max Act: 1.4055. Min Act: -0.0002

Data Index: 259474 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 1.4560. Min Range: -1.4560

Max Act: 1.1998. Min Act: -0.0002

Data Index: 206493 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 1.4560. Min Range: -1.4560

Max Act: 1.3251. Min Act: -0.0002

Data Index: 232463 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 1.4560. Min Range: -1.4560

Max Act: 1.3836. Min Act: -0.0002

Data Index: 1219392 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 1.4560. Min Range: -1.4560

Max Act: 1.2703. Min Act: -0.0002

Data Index: 75451 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 1.4560. Min Range: -1.4560

Max Act: 1.4154. Min Act: -0.0002

Data Index: 1013948 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 1.4560. Min Range: -1.4560

Max Act: 1.3374. Min Act: -0.0002

Data Index: 660683 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 1.4560. Min Range: -1.4560

Max Act: 1.3543. Min Act: -0.0002

Data Index: 514355 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 1.4560. Min Range: -1.4560

Max Act: 1.3567. Min Act: -0.0002

Data Index: 655852 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 1.4560. Min Range: -1.4560

Max Act: 1.2191. Min Act: -0.0002

Data Index: 1098483 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 1.4560. Min Range: -1.4560

Max Act: 1.1615. Min Act: -0.0002

Data Index: 559433 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 1.4560. Min Range: -1.4560

Max Act: 1.2835. Min Act: -0.0002

Data Index: 1215048 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 1.4560. Min Range: -1.4560

Max Act: 1.2142. Min Act: -0.0002

Data Index: 427886 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 1.4560. Min Range: -1.4560

Max Act: 1.1049. Min Act: -0.0002

Data Index: 451056 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 1.4560. Min Range: -1.4560

Max Act: 1.3271. Min Act: -0.0002

Data Index: 65494 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 1.4560. Min Range: -1.4560

Max Act: 1.3113. Min Act: -0.0002

Data Index: 655897 (C4 (Web Text))

Max Activating Token Index: 1016