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

Dataset: The Pile

Neuron 3764 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4780. Min Act: -0.0000

Data Index: 182446 (The Pile)

Max Activating Token Index: 652

Text #1

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.5432. Min Act: -0.0000

Data Index: 1611814 (The Pile)

Max Activating Token Index: 677

Text #2

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.5567. Min Act: -0.0000

Data Index: 1659748 (The Pile)

Max Activating Token Index: 712

Text #3

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.5245. Min Act: -0.0000

Data Index: 1080989 (The Pile)

Max Activating Token Index: 637

Text #4

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.5194. Min Act: -0.0000

Data Index: 78000 (The Pile)

Max Activating Token Index: 69

Text #5

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.5297. Min Act: -0.0000

Data Index: 585562 (The Pile)

Max Activating Token Index: 256

Text #6

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4541. Min Act: -0.0000

Data Index: 1659633 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1232018 (The Pile)

Max Activating Token Index: 267

Text #8

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4898. Min Act: -0.0000

Data Index: 74490 (The Pile)

Max Activating Token Index: 473

Text #9

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4921. Min Act: -0.0000

Data Index: 228102 (The Pile)

Max Activating Token Index: 650

Text #10

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4832. Min Act: -0.0000

Data Index: 791927 (The Pile)

Max Activating Token Index: 428

Text #11

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4907. Min Act: -0.0000

Data Index: 1500779 (The Pile)

Max Activating Token Index: 497

Text #12

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4830. Min Act: -0.0000

Data Index: 1142391 (The Pile)

Max Activating Token Index: 12

Text #13

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4133. Min Act: -0.0000

Data Index: 11376 (The Pile)

Max Activating Token Index: 820

Text #14

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4350. Min Act: -0.0000

Data Index: 705409 (The Pile)

Max Activating Token Index: 817

Text #15

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4153. Min Act: -0.0000

Data Index: 261081 (The Pile)

Max Activating Token Index: 140

Text #16

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1833168 (The Pile)

Max Activating Token Index: 240

Text #17

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4375. Min Act: -0.0000

Data Index: 1802207 (The Pile)

Max Activating Token Index: 405

Text #18

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4766. Min Act: -0.0000

Data Index: 63393 (The Pile)

Max Activating Token Index: 886

Text #19

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1435389 (The Pile)

Max Activating Token Index: 20