Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3170 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1044829 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.5661. Min Act: -0.0000

Data Index: 698743 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.5449. Min Act: -0.0000

Data Index: 1060484 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.4636. Min Act: 0.0000

Data Index: 1138557 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.5103. Min Act: -0.0000

Data Index: 671959 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.4761. Min Act: -0.0000

Data Index: 730107 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.4175. Min Act: -0.0000

Data Index: 127796 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.4194. Min Act: -0.0001

Data Index: 309954 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.4041. Min Act: -0.0000

Data Index: 560833 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.4226. Min Act: -0.0000

Data Index: 508406 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1123552 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.3896. Min Act: -0.0000

Data Index: 864885 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.3704. Min Act: -0.0000

Data Index: 1143221 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1139129 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.3607. Min Act: -0.0000

Data Index: 916182 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.3465. Min Act: -0.0000

Data Index: 146243 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.3677. Min Act: -0.0001

Data Index: 646010 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.3582. Min Act: -0.0000

Data Index: 1169106 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.3097. Min Act: -0.0000

Data Index: 537937 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.6072. Min Range: -0.6072

Max Act: 0.3545. Min Act: -0.0000

Data Index: 856927 (C4 (Web Text))

Max Activating Token Index: 561