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

Dataset: The Pile

Neuron 3144 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.8696. Min Act: -0.0000

Data Index: 935760 (The Pile)

Max Activating Token Index: 500

Text #1

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.8481. Min Act: -0.0000

Data Index: 61891 (The Pile)

Max Activating Token Index: 411

Text #2

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.7003. Min Act: -0.0000

Data Index: 1056676 (The Pile)

Max Activating Token Index: 939

Text #3

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.6910. Min Act: -0.0000

Data Index: 1414660 (The Pile)

Max Activating Token Index: 139

Text #4

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.6895. Min Act: -0.0000

Data Index: 1417447 (The Pile)

Max Activating Token Index: 836

Text #5

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.6618. Min Act: -0.0000

Data Index: 1588668 (The Pile)

Max Activating Token Index: 680

Text #6

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1686230 (The Pile)

Max Activating Token Index: 7

Text #7

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.6383. Min Act: -0.0000

Data Index: 107011 (The Pile)

Max Activating Token Index: 779

Text #8

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.6155. Min Act: -0.0000

Data Index: 214699 (The Pile)

Max Activating Token Index: 259

Text #9

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.6691. Min Act: -0.0000

Data Index: 1354903 (The Pile)

Max Activating Token Index: 411

Text #10

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.6037. Min Act: -0.0000

Data Index: 1048622 (The Pile)

Max Activating Token Index: 13

Text #11

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.6047. Min Act: -0.0000

Data Index: 825800 (The Pile)

Max Activating Token Index: 534

Text #12

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1822376 (The Pile)

Max Activating Token Index: 781

Text #13

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.5881. Min Act: -0.0000

Data Index: 661810 (The Pile)

Max Activating Token Index: 362

Text #14

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.5829. Min Act: -0.0000

Data Index: 1334718 (The Pile)

Max Activating Token Index: 64

Text #15

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.5936. Min Act: -0.0000

Data Index: 395859 (The Pile)

Max Activating Token Index: 8

Text #16

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1796695 (The Pile)

Max Activating Token Index: 591

Text #17

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.5844. Min Act: -0.0000

Data Index: 1239589 (The Pile)

Max Activating Token Index: 302

Text #18

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.5307. Min Act: -0.0000

Data Index: 976751 (The Pile)

Max Activating Token Index: 650

Text #19

Max Range: 0.8696. Min Range: -0.8696

Max Act: 0.5418. Min Act: -0.0000

Data Index: 1801774 (The Pile)

Max Activating Token Index: 82