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

Dataset: The Pile

Neuron 3645 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.2592. Min Act: -0.0000

Data Index: 1633378 (The Pile)

Max Activating Token Index: 519

Text #1

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.1869. Min Act: -0.0000

Data Index: 1798680 (The Pile)

Max Activating Token Index: 381

Text #2

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.0855. Min Act: -0.0000

Data Index: 757326 (The Pile)

Max Activating Token Index: 122

Text #3

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.0809. Min Act: -0.0000

Data Index: 658475 (The Pile)

Max Activating Token Index: 806

Text #4

Max Range: 1.2592. Min Range: -1.2592

Max Act: 1.0282. Min Act: -0.0000

Data Index: 1546862 (The Pile)

Max Activating Token Index: 111

Text #5

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.9937. Min Act: -0.0000

Data Index: 721053 (The Pile)

Max Activating Token Index: 752

Text #6

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.8305. Min Act: -0.0000

Data Index: 910799 (The Pile)

Max Activating Token Index: 330

Text #7

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.7247. Min Act: -0.0000

Data Index: 72471 (The Pile)

Max Activating Token Index: 1015

Text #8

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.9098. Min Act: -0.0000

Data Index: 1968922 (The Pile)

Max Activating Token Index: 268

Text #9

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.7730. Min Act: -0.0000

Data Index: 680834 (The Pile)

Max Activating Token Index: 155

Text #10

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.8357. Min Act: -0.0000

Data Index: 336921 (The Pile)

Max Activating Token Index: 922

Text #11

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1082433 (The Pile)

Max Activating Token Index: 931

Text #12

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.7620. Min Act: -0.0000

Data Index: 623304 (The Pile)

Max Activating Token Index: 177

Text #13

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.8065. Min Act: -0.0000

Data Index: 1372866 (The Pile)

Max Activating Token Index: 693

Text #14

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.7788. Min Act: -0.0000

Data Index: 1046787 (The Pile)

Max Activating Token Index: 660

Text #15

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.7653. Min Act: -0.0000

Data Index: 931040 (The Pile)

Max Activating Token Index: 180

Text #16

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1750499 (The Pile)

Max Activating Token Index: 132

Text #17

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.7082. Min Act: -0.0000

Data Index: 936939 (The Pile)

Max Activating Token Index: 437

Text #18

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.6857. Min Act: -0.0000

Data Index: 66771 (The Pile)

Max Activating Token Index: 817

Text #19

Max Range: 1.2592. Min Range: -1.2592

Max Act: 0.7329. Min Act: -0.0000

Data Index: 1537391 (The Pile)

Max Activating Token Index: 389