Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3966 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.3573. Min Act: -0.0000

Data Index: 1440762 (The Pile)

Max Activating Token Index: 650

Text #1

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.2888. Min Act: -0.0000

Data Index: 1415443 (The Pile)

Max Activating Token Index: 856

Text #2

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.1761. Min Act: -0.0000

Data Index: 1254461 (The Pile)

Max Activating Token Index: 87

Text #3

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.1634. Min Act: -0.0000

Data Index: 1926489 (The Pile)

Max Activating Token Index: 451

Text #4

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.0184. Min Act: -0.0000

Data Index: 328184 (The Pile)

Max Activating Token Index: 461

Text #5

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.1287. Min Act: -0.0000

Data Index: 1231534 (The Pile)

Max Activating Token Index: 622

Text #6

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.0869. Min Act: -0.0000

Data Index: 320653 (The Pile)

Max Activating Token Index: 872

Text #7

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.1155. Min Act: -0.0000

Data Index: 976762 (The Pile)

Max Activating Token Index: 736

Text #8

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.1513. Min Act: -0.0000

Data Index: 1822382 (The Pile)

Max Activating Token Index: 619

Text #9

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.1032. Min Act: -0.0000

Data Index: 1238779 (The Pile)

Max Activating Token Index: 806

Text #10

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.0868. Min Act: -0.0000

Data Index: 313321 (The Pile)

Max Activating Token Index: 938

Text #11

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.1159. Min Act: -0.0000

Data Index: 941635 (The Pile)

Max Activating Token Index: 603

Text #12

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.0743. Min Act: -0.0000

Data Index: 1163959 (The Pile)

Max Activating Token Index: 554

Text #13

Max Range: 1.3573. Min Range: -1.3573

Max Act: 0.9821. Min Act: -0.0000

Data Index: 712870 (The Pile)

Max Activating Token Index: 807

Text #14

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.1101. Min Act: -0.0000

Data Index: 1633247 (The Pile)

Max Activating Token Index: 970

Text #15

Max Range: 1.3573. Min Range: -1.3573

Max Act: 0.9254. Min Act: -0.0000

Data Index: 461512 (The Pile)

Max Activating Token Index: 863

Text #16

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.0079. Min Act: -0.0000

Data Index: 1096734 (The Pile)

Max Activating Token Index: 570

Text #17

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.0040. Min Act: -0.0000

Data Index: 329222 (The Pile)

Max Activating Token Index: 865

Text #18

Max Range: 1.3573. Min Range: -1.3573

Max Act: 0.9933. Min Act: -0.0000

Data Index: 94732 (The Pile)

Max Activating Token Index: 617

Text #19

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.0286. Min Act: -0.0000

Data Index: 1460202 (The Pile)

Max Activating Token Index: 732