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

Dataset: The Pile

Neuron 913 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: 0.9536. Min Range: -0.9536

Max Act: 0.9536. Min Act: -0.0000

Data Index: 466366 (The Pile)

Max Activating Token Index: 108

Text #1

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.9045. Min Act: -0.0000

Data Index: 382110 (The Pile)

Max Activating Token Index: 202

Text #2

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.8885. Min Act: -0.0000

Data Index: 406494 (The Pile)

Max Activating Token Index: 555

Text #3

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.9095. Min Act: -0.0000

Data Index: 1814727 (The Pile)

Max Activating Token Index: 846

Text #4

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.8275. Min Act: -0.0000

Data Index: 1681970 (The Pile)

Max Activating Token Index: 714

Text #5

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.7907. Min Act: -0.0000

Data Index: 912016 (The Pile)

Max Activating Token Index: 711

Text #6

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.7468. Min Act: -0.0000

Data Index: 1322948 (The Pile)

Max Activating Token Index: 670

Text #7

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.7319. Min Act: -0.0000

Data Index: 1568722 (The Pile)

Max Activating Token Index: 764

Text #8

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.6359. Min Act: -0.0000

Data Index: 152568 (The Pile)

Max Activating Token Index: 610

Text #9

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.7357. Min Act: -0.0000

Data Index: 458520 (The Pile)

Max Activating Token Index: 471

Text #10

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1001841 (The Pile)

Max Activating Token Index: 273

Text #11

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.6876. Min Act: -0.0000

Data Index: 212715 (The Pile)

Max Activating Token Index: 923

Text #12

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.6856. Min Act: -0.0000

Data Index: 433963 (The Pile)

Max Activating Token Index: 230

Text #13

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.6378. Min Act: -0.0000

Data Index: 466289 (The Pile)

Max Activating Token Index: 901

Text #14

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1953151 (The Pile)

Max Activating Token Index: 928

Text #15

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.6381. Min Act: -0.0000

Data Index: 14968 (The Pile)

Max Activating Token Index: 889

Text #16

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.6347. Min Act: -0.0000

Data Index: 847313 (The Pile)

Max Activating Token Index: 351

Text #17

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.6249. Min Act: -0.0000

Data Index: 209715 (The Pile)

Max Activating Token Index: 1017

Text #18

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.6487. Min Act: -0.0000

Data Index: 866626 (The Pile)

Max Activating Token Index: 708

Text #19

Max Range: 0.9536. Min Range: -0.9536

Max Act: 0.6198. Min Act: -0.0000

Data Index: 1644208 (The Pile)

Max Activating Token Index: 224