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

Dataset: The Pile

Neuron 4408 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.5919. Min Act: -0.0000

Data Index: 489366 (The Pile)

Max Activating Token Index: 965

Text #1

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.5806. Min Act: -0.0000

Data Index: 1659220 (The Pile)

Max Activating Token Index: 288

Text #2

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.0978. Min Act: -0.0000

Data Index: 524794 (The Pile)

Max Activating Token Index: 640

Text #3

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.4822. Min Act: -0.0000

Data Index: 627401 (The Pile)

Max Activating Token Index: 403

Text #4

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.3448. Min Act: -0.0000

Data Index: 952364 (The Pile)

Max Activating Token Index: 294

Text #5

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.6281. Min Act: -0.0000

Data Index: 1033469 (The Pile)

Max Activating Token Index: 621

Text #6

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.3048. Min Act: -0.0000

Data Index: 1415206 (The Pile)

Max Activating Token Index: 1011

Text #7

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.5090. Min Act: -0.0000

Data Index: 407549 (The Pile)

Max Activating Token Index: 233

Text #8

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.4438. Min Act: -0.0000

Data Index: 229701 (The Pile)

Max Activating Token Index: 444

Text #9

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.5786. Min Act: -0.0000

Data Index: 1670854 (The Pile)

Max Activating Token Index: 497

Text #10

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.4357. Min Act: -0.0000

Data Index: 325609 (The Pile)

Max Activating Token Index: 604

Text #11

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.4824. Min Act: -0.0000

Data Index: 465741 (The Pile)

Max Activating Token Index: 929

Text #12

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.1990. Min Act: -0.0000

Data Index: 740965 (The Pile)

Max Activating Token Index: 722

Text #13

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.3761. Min Act: -0.0000

Data Index: 38102 (The Pile)

Max Activating Token Index: 604

Text #14

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.4887. Min Act: -0.0000

Data Index: 1076864 (The Pile)

Max Activating Token Index: 180

Text #15

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.2543. Min Act: -0.0000

Data Index: 192973 (The Pile)

Max Activating Token Index: 799

Text #16

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.2358. Min Act: -0.0000

Data Index: 400478 (The Pile)

Max Activating Token Index: 316

Text #17

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.5372. Min Act: -0.0000

Data Index: 557816 (The Pile)

Max Activating Token Index: 913

Text #18

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.1776. Min Act: -0.0000

Data Index: 1738857 (The Pile)

Max Activating Token Index: 552

Text #19

Max Range: 1.6281. Min Range: -1.6281

Max Act: 1.4531. Min Act: -0.0000

Data Index: 57326 (The Pile)

Max Activating Token Index: 973