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

Dataset: The Pile

Neuron 3394 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: 0.6869. Min Range: -0.6869

Max Act: 0.6869. Min Act: -0.0000

Data Index: 595779 (The Pile)

Max Activating Token Index: 913

Text #1

Max Range: 0.6869. Min Range: -0.6869

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1541718 (The Pile)

Max Activating Token Index: 1013

Text #2

Max Range: 0.6869. Min Range: -0.6869

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1147774 (The Pile)

Max Activating Token Index: 55

Text #3

Max Range: 0.6869. Min Range: -0.6869

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1769269 (The Pile)

Max Activating Token Index: 163

Text #4

Max Range: 0.6869. Min Range: -0.6869

Max Act: 0.6242. Min Act: -0.0000

Data Index: 867310 (The Pile)

Max Activating Token Index: 955

Text #5

Max Range: 0.6869. Min Range: -0.6869

Max Act: 0.5909. Min Act: -0.0000

Data Index: 1910455 (The Pile)

Max Activating Token Index: 930

Text #6

Max Range: 0.6869. Min Range: -0.6869

Max Act: 0.5946. Min Act: -0.0000

Data Index: 654315 (The Pile)

Max Activating Token Index: 856

Text #7

Max Range: 0.6869. Min Range: -0.6869

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1932013 (The Pile)

Max Activating Token Index: 417

Text #8

Max Range: 0.6869. Min Range: -0.6869

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1251915 (The Pile)

Max Activating Token Index: 110

Text #9

Max Range: 0.6869. Min Range: -0.6869

Max Act: 0.5677. Min Act: -0.0000

Data Index: 1482992 (The Pile)

Max Activating Token Index: 113

Text #10

Max Range: 0.6869. Min Range: -0.6869

Max Act: 0.5673. Min Act: -0.0000

Data Index: 1814137 (The Pile)

Max Activating Token Index: 750

Text #11

Max Range: 0.6869. Min Range: -0.6869

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1419910 (The Pile)

Max Activating Token Index: 126

Text #12

Max Range: 0.6869. Min Range: -0.6869

Max Act: 0.5656. Min Act: -0.0000

Data Index: 342371 (The Pile)

Max Activating Token Index: 590

Text #13

Max Range: 0.6869. Min Range: -0.6869

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1802464 (The Pile)

Max Activating Token Index: 918

Text #14

Max Range: 0.6869. Min Range: -0.6869

Max Act: 0.5129. Min Act: -0.0000

Data Index: 1238698 (The Pile)

Max Activating Token Index: 930

Text #15

Max Range: 0.6869. Min Range: -0.6869

Max Act: 0.5253. Min Act: -0.0000

Data Index: 1787346 (The Pile)

Max Activating Token Index: 525

Text #16

Max Range: 0.6869. Min Range: -0.6869

Max Act: 0.5216. Min Act: -0.0000

Data Index: 949240 (The Pile)

Max Activating Token Index: 690

Text #17

Max Range: 0.6869. Min Range: -0.6869

Max Act: 0.5352. Min Act: -0.0000

Data Index: 913927 (The Pile)

Max Activating Token Index: 38

Text #18

Max Range: 0.6869. Min Range: -0.6869

Max Act: 0.4928. Min Act: -0.0000

Data Index: 973376 (The Pile)

Max Activating Token Index: 289

Text #19

Max Range: 0.6869. Min Range: -0.6869

Max Act: 0.4755. Min Act: -0.0000

Data Index: 910860 (The Pile)

Max Activating Token Index: 723