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

Dataset: The Pile

Neuron 1516 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.9088. Min Act: -0.0000

Data Index: 1492916 (The Pile)

Max Activating Token Index: 976

Text #1

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7012. Min Act: -0.0000

Data Index: 1417318 (The Pile)

Max Activating Token Index: 632

Text #2

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.6706. Min Act: -0.0000

Data Index: 120596 (The Pile)

Max Activating Token Index: 827

Text #3

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.6888. Min Act: -0.0000

Data Index: 289278 (The Pile)

Max Activating Token Index: 730

Text #4

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.6515. Min Act: -0.0000

Data Index: 63818 (The Pile)

Max Activating Token Index: 435

Text #5

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1997933 (The Pile)

Max Activating Token Index: 613

Text #6

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.6308. Min Act: -0.0000

Data Index: 966639 (The Pile)

Max Activating Token Index: 359

Text #7

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.5845. Min Act: -0.0000

Data Index: 712000 (The Pile)

Max Activating Token Index: 624

Text #8

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1098649 (The Pile)

Max Activating Token Index: 517

Text #9

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.5412. Min Act: -0.0000

Data Index: 691965 (The Pile)

Max Activating Token Index: 228

Text #10

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1846773 (The Pile)

Max Activating Token Index: 399

Text #11

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.5332. Min Act: -0.0000

Data Index: 328151 (The Pile)

Max Activating Token Index: 230

Text #12

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.5626. Min Act: -0.0000

Data Index: 111551 (The Pile)

Max Activating Token Index: 365

Text #13

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1128000 (The Pile)

Max Activating Token Index: 470

Text #14

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.5299. Min Act: -0.0000

Data Index: 1939095 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.4852. Min Act: -0.0000

Data Index: 913134 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.4792. Min Act: -0.0000

Data Index: 1369968 (The Pile)

Max Activating Token Index: 642

Text #17

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.4630. Min Act: -0.0000

Data Index: 883036 (The Pile)

Max Activating Token Index: 510

Text #18

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.4830. Min Act: -0.0000

Data Index: 390728 (The Pile)

Max Activating Token Index: 508

Text #19

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.4875. Min Act: -0.0000

Data Index: 1167186 (The Pile)

Max Activating Token Index: 566