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

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

Neuron 4147 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2730. Min Range: -1.2730

Max Act: 1.2730. Min Act: -0.0000

Data Index: 1106389 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 1.2730. Min Range: -1.2730

Max Act: 1.1223. Min Act: -0.0000

Data Index: 918231 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 1.2730. Min Range: -1.2730

Max Act: 1.0277. Min Act: -0.0000

Data Index: 964838 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 1.2730. Min Range: -1.2730

Max Act: 1.1464. Min Act: -0.0000

Data Index: 1355329 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.9941. Min Act: -0.0000

Data Index: 498680 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.9856. Min Act: -0.0000

Data Index: 1069337 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 1.2730. Min Range: -1.2730

Max Act: 1.0458. Min Act: -0.0000

Data Index: 420027 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.9652. Min Act: -0.0000

Data Index: 970969 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.9802. Min Act: -0.0000

Data Index: 684930 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.8905. Min Act: -0.0000

Data Index: 996740 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.8691. Min Act: -0.0000

Data Index: 1014138 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.8667. Min Act: -0.0000

Data Index: 924701 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.8909. Min Act: -0.0000

Data Index: 966383 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.8082. Min Act: -0.0000

Data Index: 456267 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.8327. Min Act: -0.0000

Data Index: 278716 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.8043. Min Act: -0.0000

Data Index: 748973 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.8487. Min Act: -0.0000

Data Index: 277973 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.8918. Min Act: -0.0000

Data Index: 785418 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.8267. Min Act: -0.0000

Data Index: 295982 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 1.2730. Min Range: -1.2730

Max Act: 0.8742. Min Act: -0.0000

Data Index: 1337233 (C4 (Web Text))

Max Activating Token Index: 331