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

Dataset: The Pile

Neuron 978 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: 0.5399. Min Range: -0.5399

Max Act: 0.5399. Min Act: -0.0000

Data Index: 919908 (The Pile)

Max Activating Token Index: 724

Text #1

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1784567 (The Pile)

Max Activating Token Index: 79

Text #2

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1994589 (The Pile)

Max Activating Token Index: 588

Text #3

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4561. Min Act: -0.0000

Data Index: 652053 (The Pile)

Max Activating Token Index: 568

Text #4

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4663. Min Act: -0.0000

Data Index: 899522 (The Pile)

Max Activating Token Index: 147

Text #5

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1653265 (The Pile)

Max Activating Token Index: 993

Text #6

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1936633 (The Pile)

Max Activating Token Index: 171

Text #7

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4384. Min Act: -0.0000

Data Index: 716427 (The Pile)

Max Activating Token Index: 705

Text #8

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1477407 (The Pile)

Max Activating Token Index: 205

Text #9

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4153. Min Act: -0.0000

Data Index: 41149 (The Pile)

Max Activating Token Index: 18

Text #10

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4036. Min Act: -0.0000

Data Index: 261159 (The Pile)

Max Activating Token Index: 64

Text #11

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4288. Min Act: -0.0000

Data Index: 308175 (The Pile)

Max Activating Token Index: 403

Text #12

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1829492 (The Pile)

Max Activating Token Index: 9

Text #13

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3729. Min Act: -0.0000

Data Index: 825022 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3795. Min Act: -0.0000

Data Index: 326057 (The Pile)

Max Activating Token Index: 629

Text #15

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3679. Min Act: -0.0000

Data Index: 1809693 (The Pile)

Max Activating Token Index: 917

Text #16

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3572. Min Act: -0.0000

Data Index: 652537 (The Pile)

Max Activating Token Index: 198

Text #17

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3664. Min Act: -0.0000

Data Index: 1387224 (The Pile)

Max Activating Token Index: 326

Text #18

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1107883 (The Pile)

Max Activating Token Index: 308

Text #19

Max Range: 0.5399. Min Range: -0.5399

Max Act: 0.3579. Min Act: -0.0000

Data Index: 820836 (The Pile)

Max Activating Token Index: 604