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

Dataset: The Pile

Neuron 3505 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.2858. Min Act: -0.0000

Data Index: 861789 (The Pile)

Max Activating Token Index: 64

Text #1

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.1338. Min Act: -0.0000

Data Index: 881872 (The Pile)

Max Activating Token Index: 381

Text #2

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.1931. Min Act: -0.0000

Data Index: 1740981 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.1727. Min Act: -0.0000

Data Index: 34660 (The Pile)

Max Activating Token Index: 476

Text #4

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.1055. Min Act: -0.0000

Data Index: 527409 (The Pile)

Max Activating Token Index: 491

Text #5

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.0475. Min Act: -0.0000

Data Index: 954774 (The Pile)

Max Activating Token Index: 501

Text #6

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.1045. Min Act: -0.0000

Data Index: 758465 (The Pile)

Max Activating Token Index: 708

Text #7

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.1599. Min Act: -0.0000

Data Index: 1298866 (The Pile)

Max Activating Token Index: 101

Text #8

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.1187. Min Act: -0.0000

Data Index: 1296062 (The Pile)

Max Activating Token Index: 520

Text #9

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.9704. Min Act: -0.0000

Data Index: 657668 (The Pile)

Max Activating Token Index: 107

Text #10

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.9012. Min Act: -0.0000

Data Index: 1613829 (The Pile)

Max Activating Token Index: 827

Text #11

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.9175. Min Act: -0.0000

Data Index: 297500 (The Pile)

Max Activating Token Index: 236

Text #12

Max Range: 1.2858. Min Range: -1.2858

Max Act: 1.1545. Min Act: -0.0000

Data Index: 1439208 (The Pile)

Max Activating Token Index: 875

Text #13

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.8573. Min Act: -0.0000

Data Index: 1935674 (The Pile)

Max Activating Token Index: 155

Text #14

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.9520. Min Act: -0.0000

Data Index: 1472148 (The Pile)

Max Activating Token Index: 113

Text #15

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.9162. Min Act: -0.0000

Data Index: 1256529 (The Pile)

Max Activating Token Index: 94

Text #16

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.9758. Min Act: -0.0000

Data Index: 638842 (The Pile)

Max Activating Token Index: 476

Text #17

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.9525. Min Act: -0.0000

Data Index: 543984 (The Pile)

Max Activating Token Index: 351

Text #18

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.9742. Min Act: -0.0000

Data Index: 153049 (The Pile)

Max Activating Token Index: 473

Text #19

Max Range: 1.2858. Min Range: -1.2858

Max Act: 0.8966. Min Act: -0.0000

Data Index: 233079 (The Pile)

Max Activating Token Index: 638