Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2408 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3599. Min Act: -0.0003

Data Index: 747259 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.4218. Min Act: -0.0003

Data Index: 497696 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3876. Min Act: -0.0003

Data Index: 1086041 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3920. Min Act: -0.0003

Data Index: 493838 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.4056. Min Act: -0.0003

Data Index: 796246 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3743. Min Act: -0.0003

Data Index: 439294 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3664. Min Act: -0.0003

Data Index: 972218 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3973. Min Act: -0.0003

Data Index: 1313253 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3584. Min Act: -0.0003

Data Index: 1232267 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3548. Min Act: -0.0003

Data Index: 541681 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3486. Min Act: -0.0003

Data Index: 1192703 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3683. Min Act: -0.0003

Data Index: 253278 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3691. Min Act: -0.0003

Data Index: 450711 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3672. Min Act: -0.0003

Data Index: 408907 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3793. Min Act: -0.0003

Data Index: 469671 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3507. Min Act: -0.0003

Data Index: 339750 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3791. Min Act: -0.0003

Data Index: 1510587 (Python Code)

Max Activating Token Index: 260

Text #17

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3546. Min Act: -0.0003

Data Index: 1131252 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3499. Min Act: -0.0003

Data Index: 1011851 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.2156. Min Act: -0.0003

Data Index: 614090 (C4 (Web Text))

Max Activating Token Index: 854