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

Dataset: The Pile

Neuron 4828 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: 1.9450. Min Range: -1.9450

Max Act: 1.9450. Min Act: -0.0000

Data Index: 1350935 (The Pile)

Max Activating Token Index: 142

Text #1

Max Range: 1.9450. Min Range: -1.9450

Max Act: 1.6246. Min Act: -0.0000

Data Index: 1555850 (The Pile)

Max Activating Token Index: 200

Text #2

Max Range: 1.9450. Min Range: -1.9450

Max Act: 1.6148. Min Act: -0.0000

Data Index: 977012 (The Pile)

Max Activating Token Index: 119

Text #3

Max Range: 1.9450. Min Range: -1.9450

Max Act: 1.4731. Min Act: -0.0000

Data Index: 1300691 (The Pile)

Max Activating Token Index: 645

Text #4

Max Range: 1.9450. Min Range: -1.9450

Max Act: 1.3680. Min Act: -0.0000

Data Index: 47833 (The Pile)

Max Activating Token Index: 850

Text #5

Max Range: 1.9450. Min Range: -1.9450

Max Act: 1.5911. Min Act: -0.0000

Data Index: 636558 (The Pile)

Max Activating Token Index: 849

Text #6

Max Range: 1.9450. Min Range: -1.9450

Max Act: 1.3978. Min Act: -0.0000

Data Index: 703074 (The Pile)

Max Activating Token Index: 323

Text #7

Max Range: 1.9450. Min Range: -1.9450

Max Act: 1.4408. Min Act: -0.0000

Data Index: 691553 (The Pile)

Max Activating Token Index: 816

Text #8

Max Range: 1.9450. Min Range: -1.9450

Max Act: 1.4258. Min Act: -0.0000

Data Index: 1300433 (The Pile)

Max Activating Token Index: 942

Text #9

Max Range: 1.9450. Min Range: -1.9450

Max Act: 1.4228. Min Act: -0.0000

Data Index: 1141494 (The Pile)

Max Activating Token Index: 540

Text #10

Max Range: 1.9450. Min Range: -1.9450

Max Act: 1.2758. Min Act: -0.0000

Data Index: 1599765 (The Pile)

Max Activating Token Index: 973

Text #11

Max Range: 1.9450. Min Range: -1.9450

Max Act: 1.3447. Min Act: -0.0000

Data Index: 906934 (The Pile)

Max Activating Token Index: 1019

Text #12

Max Range: 1.9450. Min Range: -1.9450

Max Act: 1.4880. Min Act: -0.0000

Data Index: 1823934 (The Pile)

Max Activating Token Index: 523

Text #13

Max Range: 1.9450. Min Range: -1.9450

Max Act: 1.3847. Min Act: -0.0000

Data Index: 701932 (The Pile)

Max Activating Token Index: 566

Text #14

Max Range: 1.9450. Min Range: -1.9450

Max Act: 1.3639. Min Act: -0.0000

Data Index: 1482843 (The Pile)

Max Activating Token Index: 694

Text #15

Max Range: 1.9450. Min Range: -1.9450

Max Act: 1.3586. Min Act: -0.0000

Data Index: 1166267 (The Pile)

Max Activating Token Index: 956

Text #16

Max Range: 1.9450. Min Range: -1.9450

Max Act: 1.2712. Min Act: -0.0000

Data Index: 471207 (The Pile)

Max Activating Token Index: 908

Text #17

Max Range: 1.9450. Min Range: -1.9450

Max Act: 1.2642. Min Act: -0.0000

Data Index: 281859 (The Pile)

Max Activating Token Index: 38

Text #18

Max Range: 1.9450. Min Range: -1.9450

Max Act: 1.4221. Min Act: -0.0000

Data Index: 508147 (The Pile)

Max Activating Token Index: 442

Text #19

Max Range: 1.9450. Min Range: -1.9450

Max Act: 1.2628. Min Act: -0.0000

Data Index: 1346408 (The Pile)

Max Activating Token Index: 240