Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3824 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.5253. Min Act: -0.0000

Data Index: 1838876 (The Pile)

Max Activating Token Index: 573

Text #1

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4825. Min Act: -0.0000

Data Index: 21513 (The Pile)

Max Activating Token Index: 684

Text #2

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4501. Min Act: -0.0000

Data Index: 1133318 (The Pile)

Max Activating Token Index: 62

Text #3

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1343512 (The Pile)

Max Activating Token Index: 557

Text #4

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4294. Min Act: -0.0000

Data Index: 1522745 (The Pile)

Max Activating Token Index: 1011

Text #5

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4293. Min Act: -0.0000

Data Index: 1241540 (The Pile)

Max Activating Token Index: 294

Text #6

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4096. Min Act: -0.0000

Data Index: 610458 (The Pile)

Max Activating Token Index: 481

Text #7

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3852. Min Act: -0.0000

Data Index: 83923 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3889. Min Act: -0.0000

Data Index: 540836 (The Pile)

Max Activating Token Index: 682

Text #9

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3794. Min Act: -0.0000

Data Index: 989883 (The Pile)

Max Activating Token Index: 178

Text #10

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3884. Min Act: -0.0000

Data Index: 118033 (The Pile)

Max Activating Token Index: 29

Text #11

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3684. Min Act: -0.0000

Data Index: 1735309 (The Pile)

Max Activating Token Index: 346

Text #12

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3795. Min Act: -0.0000

Data Index: 1478920 (The Pile)

Max Activating Token Index: 66

Text #13

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3507. Min Act: -0.0000

Data Index: 597276 (The Pile)

Max Activating Token Index: 237

Text #14

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3551. Min Act: -0.0000

Data Index: 123987 (The Pile)

Max Activating Token Index: 105

Text #15

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1853655 (The Pile)

Max Activating Token Index: 760

Text #16

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3374. Min Act: -0.0000

Data Index: 743766 (The Pile)

Max Activating Token Index: 849

Text #17

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1400713 (The Pile)

Max Activating Token Index: 477

Text #18

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3457. Min Act: -0.0000

Data Index: 421101 (The Pile)

Max Activating Token Index: 486

Text #19

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3685. Min Act: -0.0000

Data Index: 309310 (The Pile)

Max Activating Token Index: 604