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

Dataset: The Pile

Neuron 2268 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: 0.7602. Min Range: -0.7602

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1751141 (The Pile)

Max Activating Token Index: 676

Text #1

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.7389. Min Act: -0.0000

Data Index: 570126 (The Pile)

Max Activating Token Index: 723

Text #2

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.7602. Min Act: -0.0000

Data Index: 501732 (The Pile)

Max Activating Token Index: 785

Text #3

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.7048. Min Act: -0.0000

Data Index: 718601 (The Pile)

Max Activating Token Index: 59

Text #4

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1004034 (The Pile)

Max Activating Token Index: 566

Text #5

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6757. Min Act: -0.0000

Data Index: 657039 (The Pile)

Max Activating Token Index: 76

Text #6

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6949. Min Act: -0.0000

Data Index: 729784 (The Pile)

Max Activating Token Index: 1007

Text #7

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6750. Min Act: -0.0000

Data Index: 666013 (The Pile)

Max Activating Token Index: 609

Text #8

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6300. Min Act: -0.0000

Data Index: 826073 (The Pile)

Max Activating Token Index: 620

Text #9

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1414320 (The Pile)

Max Activating Token Index: 372

Text #10

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6612. Min Act: -0.0000

Data Index: 449153 (The Pile)

Max Activating Token Index: 1020

Text #11

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6486. Min Act: 0.0000

Data Index: 394268 (The Pile)

Max Activating Token Index: 781

Text #12

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6252. Min Act: -0.0000

Data Index: 769516 (The Pile)

Max Activating Token Index: 397

Text #13

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6350. Min Act: -0.0000

Data Index: 168966 (The Pile)

Max Activating Token Index: 800

Text #14

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.5961. Min Act: -0.0000

Data Index: 433681 (The Pile)

Max Activating Token Index: 981

Text #15

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6143. Min Act: -0.0000

Data Index: 432979 (The Pile)

Max Activating Token Index: 373

Text #16

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6475. Min Act: 0.0000

Data Index: 8247 (The Pile)

Max Activating Token Index: 931

Text #17

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1112532 (The Pile)

Max Activating Token Index: 867

Text #18

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1190248 (The Pile)

Max Activating Token Index: 924

Text #19

Max Range: 0.7602. Min Range: -0.7602

Max Act: 0.5966. Min Act: -0.0000

Data Index: 548582 (The Pile)

Max Activating Token Index: 853