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

Dataset: The Pile

Neuron 470 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.8339. Min Act: -0.0000

Data Index: 679868 (The Pile)

Max Activating Token Index: 866

Text #1

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.3477. Min Act: -0.0000

Data Index: 1880949 (The Pile)

Max Activating Token Index: 604

Text #2

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.4181. Min Act: -0.0000

Data Index: 1289378 (The Pile)

Max Activating Token Index: 416

Text #3

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.3685. Min Act: -0.0000

Data Index: 1893799 (The Pile)

Max Activating Token Index: 529

Text #4

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.4277. Min Act: -0.0000

Data Index: 312919 (The Pile)

Max Activating Token Index: 48

Text #5

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.3693. Min Act: -0.0000

Data Index: 898303 (The Pile)

Max Activating Token Index: 549

Text #6

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.4445. Min Act: -0.0000

Data Index: 1556137 (The Pile)

Max Activating Token Index: 71

Text #7

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.5097. Min Act: -0.0000

Data Index: 289960 (The Pile)

Max Activating Token Index: 181

Text #8

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.3295. Min Act: -0.0000

Data Index: 1790505 (The Pile)

Max Activating Token Index: 49

Text #9

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.2783. Min Act: -0.0000

Data Index: 792267 (The Pile)

Max Activating Token Index: 279

Text #10

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.1251. Min Act: -0.0000

Data Index: 432340 (The Pile)

Max Activating Token Index: 765

Text #11

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.2853. Min Act: -0.0000

Data Index: 458075 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.2902. Min Act: -0.0000

Data Index: 1052627 (The Pile)

Max Activating Token Index: 675

Text #13

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.2433. Min Act: -0.0000

Data Index: 1037265 (The Pile)

Max Activating Token Index: 579

Text #14

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.2005. Min Act: -0.0000

Data Index: 1235044 (The Pile)

Max Activating Token Index: 60

Text #15

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.2738. Min Act: -0.0000

Data Index: 1815466 (The Pile)

Max Activating Token Index: 636

Text #16

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.3252. Min Act: -0.0000

Data Index: 1894694 (The Pile)

Max Activating Token Index: 617

Text #17

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.1194. Min Act: -0.0000

Data Index: 1018102 (The Pile)

Max Activating Token Index: 220

Text #18

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.2328. Min Act: -0.0000

Data Index: 1468420 (The Pile)

Max Activating Token Index: 152

Text #19

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.1851. Min Act: -0.0000

Data Index: 1993153 (The Pile)

Max Activating Token Index: 553