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

Dataset: The Pile

Neuron 2851 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.8411. Min Act: -0.0000

Data Index: 1101614 (The Pile)

Max Activating Token Index: 1013

Text #1

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7919. Min Act: -0.0000

Data Index: 1956493 (The Pile)

Max Activating Token Index: 366

Text #2

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6413. Min Act: -0.0000

Data Index: 198918 (The Pile)

Max Activating Token Index: 314

Text #3

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5970. Min Act: -0.0000

Data Index: 596047 (The Pile)

Max Activating Token Index: 63

Text #4

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5694. Min Act: -0.0000

Data Index: 292642 (The Pile)

Max Activating Token Index: 250

Text #5

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1472732 (The Pile)

Max Activating Token Index: 85

Text #6

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1733396 (The Pile)

Max Activating Token Index: 944

Text #7

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1711396 (The Pile)

Max Activating Token Index: 98

Text #8

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6000. Min Act: -0.0000

Data Index: 396838 (The Pile)

Max Activating Token Index: 872

Text #9

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1509106 (The Pile)

Max Activating Token Index: 821

Text #10

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5527. Min Act: -0.0000

Data Index: 348500 (The Pile)

Max Activating Token Index: 723

Text #11

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5804. Min Act: -0.0000

Data Index: 872290 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5384. Min Act: -0.0000

Data Index: 1052884 (The Pile)

Max Activating Token Index: 89

Text #13

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5580. Min Act: -0.0000

Data Index: 665463 (The Pile)

Max Activating Token Index: 884

Text #14

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5234. Min Act: -0.0000

Data Index: 265481 (The Pile)

Max Activating Token Index: 1012

Text #15

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5496. Min Act: -0.0000

Data Index: 855878 (The Pile)

Max Activating Token Index: 775

Text #16

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5145. Min Act: -0.0000

Data Index: 603366 (The Pile)

Max Activating Token Index: 67

Text #17

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.4995. Min Act: -0.0000

Data Index: 273026 (The Pile)

Max Activating Token Index: 806

Text #18

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5137. Min Act: -0.0000

Data Index: 1025423 (The Pile)

Max Activating Token Index: 30

Text #19

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.4947. Min Act: -0.0000

Data Index: 871098 (The Pile)

Max Activating Token Index: 580