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

Dataset: The Pile

Neuron 2437 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: 0.9579. Min Range: -0.9579

Max Act: 0.9579. Min Act: -0.0000

Data Index: 574939 (The Pile)

Max Activating Token Index: 69

Text #1

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.8807. Min Act: -0.0000

Data Index: 1766696 (The Pile)

Max Activating Token Index: 197

Text #2

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.8383. Min Act: -0.0000

Data Index: 906581 (The Pile)

Max Activating Token Index: 576

Text #3

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.8468. Min Act: -0.0000

Data Index: 1652710 (The Pile)

Max Activating Token Index: 80

Text #4

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.8573. Min Act: -0.0000

Data Index: 652333 (The Pile)

Max Activating Token Index: 37

Text #5

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.9345. Min Act: -0.0000

Data Index: 267704 (The Pile)

Max Activating Token Index: 348

Text #6

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1990443 (The Pile)

Max Activating Token Index: 922

Text #7

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.8016. Min Act: -0.0000

Data Index: 888728 (The Pile)

Max Activating Token Index: 344

Text #8

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7987. Min Act: -0.0000

Data Index: 1119240 (The Pile)

Max Activating Token Index: 632

Text #9

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7596. Min Act: -0.0000

Data Index: 372382 (The Pile)

Max Activating Token Index: 932

Text #10

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7935. Min Act: -0.0000

Data Index: 645856 (The Pile)

Max Activating Token Index: 393

Text #11

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7418. Min Act: -0.0000

Data Index: 1462314 (The Pile)

Max Activating Token Index: 133

Text #12

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7608. Min Act: -0.0000

Data Index: 70357 (The Pile)

Max Activating Token Index: 399

Text #13

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7981. Min Act: -0.0000

Data Index: 441223 (The Pile)

Max Activating Token Index: 188

Text #14

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7220. Min Act: -0.0000

Data Index: 1815328 (The Pile)

Max Activating Token Index: 26

Text #15

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7518. Min Act: -0.0000

Data Index: 106313 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7453. Min Act: -0.0000

Data Index: 501079 (The Pile)

Max Activating Token Index: 70

Text #17

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7532. Min Act: -0.0000

Data Index: 1568102 (The Pile)

Max Activating Token Index: 35

Text #18

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1853632 (The Pile)

Max Activating Token Index: 928

Text #19

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7219. Min Act: -0.0000

Data Index: 1427344 (The Pile)

Max Activating Token Index: 92