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

Dataset: The Pile

Neuron 4778 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.5207. Min Act: -0.0000

Data Index: 191446 (The Pile)

Max Activating Token Index: 604

Text #1

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.2838. Min Act: -0.0000

Data Index: 1824726 (The Pile)

Max Activating Token Index: 741

Text #2

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.3578. Min Act: -0.0000

Data Index: 723212 (The Pile)

Max Activating Token Index: 409

Text #3

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.2258. Min Act: -0.0000

Data Index: 929273 (The Pile)

Max Activating Token Index: 107

Text #4

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.1777. Min Act: -0.0000

Data Index: 982961 (The Pile)

Max Activating Token Index: 647

Text #5

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.1093. Min Act: -0.0000

Data Index: 497213 (The Pile)

Max Activating Token Index: 53

Text #6

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.2068. Min Act: -0.0000

Data Index: 1557999 (The Pile)

Max Activating Token Index: 467

Text #7

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.1948. Min Act: -0.0000

Data Index: 1306660 (The Pile)

Max Activating Token Index: 525

Text #8

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.0908. Min Act: -0.0000

Data Index: 1300688 (The Pile)

Max Activating Token Index: 896

Text #9

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.0166. Min Act: -0.0000

Data Index: 287696 (The Pile)

Max Activating Token Index: 575

Text #10

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.0518. Min Act: -0.0000

Data Index: 1248515 (The Pile)

Max Activating Token Index: 912

Text #11

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.0367. Min Act: -0.0000

Data Index: 20700 (The Pile)

Max Activating Token Index: 197

Text #12

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.0244. Min Act: -0.0000

Data Index: 413196 (The Pile)

Max Activating Token Index: 162

Text #13

Max Range: 1.5207. Min Range: -1.5207

Max Act: 0.9571. Min Act: -0.0000

Data Index: 1550242 (The Pile)

Max Activating Token Index: 684

Text #14

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.0725. Min Act: -0.0000

Data Index: 49785 (The Pile)

Max Activating Token Index: 384

Text #15

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.0830. Min Act: -0.0000

Data Index: 549121 (The Pile)

Max Activating Token Index: 875

Text #16

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.0765. Min Act: -0.0000

Data Index: 1192187 (The Pile)

Max Activating Token Index: 437

Text #17

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.0065. Min Act: -0.0000

Data Index: 1925129 (The Pile)

Max Activating Token Index: 91

Text #18

Max Range: 1.5207. Min Range: -1.5207

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1581569 (The Pile)

Max Activating Token Index: 563

Text #19

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.0636. Min Act: -0.0000

Data Index: 1758945 (The Pile)

Max Activating Token Index: 260