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

Dataset: The Pile

Neuron 3312 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: 0.9103. Min Range: -0.9103

Max Act: 0.8205. Min Act: -0.0000

Data Index: 47724 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.9103. Min Act: -0.0000

Data Index: 1685256 (The Pile)

Max Activating Token Index: 840

Text #2

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1213151 (The Pile)

Max Activating Token Index: 445

Text #3

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1849717 (The Pile)

Max Activating Token Index: 66

Text #4

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.7548. Min Act: -0.0000

Data Index: 225526 (The Pile)

Max Activating Token Index: 768

Text #5

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1067359 (The Pile)

Max Activating Token Index: 980

Text #6

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.7668. Min Act: -0.0000

Data Index: 630769 (The Pile)

Max Activating Token Index: 367

Text #7

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.7491. Min Act: -0.0000

Data Index: 1782101 (The Pile)

Max Activating Token Index: 582

Text #8

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1179756 (The Pile)

Max Activating Token Index: 31

Text #9

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1758805 (The Pile)

Max Activating Token Index: 968

Text #10

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.7244. Min Act: -0.0000

Data Index: 1010901 (The Pile)

Max Activating Token Index: 474

Text #11

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.7137. Min Act: -0.0000

Data Index: 1169502 (The Pile)

Max Activating Token Index: 544

Text #12

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.7062. Min Act: -0.0000

Data Index: 1881155 (The Pile)

Max Activating Token Index: 734

Text #13

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.6026. Min Act: -0.0000

Data Index: 950502 (The Pile)

Max Activating Token Index: 1012

Text #14

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1870587 (The Pile)

Max Activating Token Index: 722

Text #15

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1739971 (The Pile)

Max Activating Token Index: 454

Text #16

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.6157. Min Act: -0.0000

Data Index: 1927276 (The Pile)

Max Activating Token Index: 947

Text #17

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.6402. Min Act: -0.0000

Data Index: 383972 (The Pile)

Max Activating Token Index: 806

Text #18

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.6709. Min Act: -0.0000

Data Index: 126722 (The Pile)

Max Activating Token Index: 655

Text #19

Max Range: 0.9103. Min Range: -0.9103

Max Act: 0.6510. Min Act: -0.0000

Data Index: 926090 (The Pile)

Max Activating Token Index: 699