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

Dataset: The Pile

Neuron 2692 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: 0.9007. Min Range: -0.9007

Max Act: 0.8834. Min Act: -0.0000

Data Index: 1540310 (The Pile)

Max Activating Token Index: 751

Text #1

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.8460. Min Act: -0.0000

Data Index: 626653 (The Pile)

Max Activating Token Index: 25

Text #2

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.8393. Min Act: -0.0000

Data Index: 303345 (The Pile)

Max Activating Token Index: 923

Text #3

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.7567. Min Act: -0.0000

Data Index: 1243692 (The Pile)

Max Activating Token Index: 496

Text #4

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.9007. Min Act: -0.0000

Data Index: 1615919 (The Pile)

Max Activating Token Index: 603

Text #5

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.8625. Min Act: -0.0000

Data Index: 728650 (The Pile)

Max Activating Token Index: 599

Text #6

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.8511. Min Act: -0.0000

Data Index: 1500120 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.8249. Min Act: -0.0000

Data Index: 903862 (The Pile)

Max Activating Token Index: 549

Text #8

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.8483. Min Act: -0.0000

Data Index: 1943945 (The Pile)

Max Activating Token Index: 746

Text #9

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.8728. Min Act: -0.0000

Data Index: 1452244 (The Pile)

Max Activating Token Index: 648

Text #10

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.8160. Min Act: -0.0000

Data Index: 1686854 (The Pile)

Max Activating Token Index: 667

Text #11

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.8103. Min Act: -0.0000

Data Index: 1400823 (The Pile)

Max Activating Token Index: 690

Text #12

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.8193. Min Act: -0.0000

Data Index: 907895 (The Pile)

Max Activating Token Index: 343

Text #13

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.7823. Min Act: -0.0000

Data Index: 1927582 (The Pile)

Max Activating Token Index: 928

Text #14

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1305902 (The Pile)

Max Activating Token Index: 530

Text #15

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.7754. Min Act: -0.0000

Data Index: 788193 (The Pile)

Max Activating Token Index: 686

Text #16

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.7875. Min Act: -0.0000

Data Index: 1421367 (The Pile)

Max Activating Token Index: 680

Text #17

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.8399. Min Act: -0.0000

Data Index: 739960 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.8596. Min Act: -0.0000

Data Index: 489676 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1913829 (The Pile)

Max Activating Token Index: 369