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

Dataset: The Pile

Neuron 2021 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0090. Min Act: -0.0000

Data Index: 1359309 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0088. Min Act: -0.0001

Data Index: 1766441 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0087. Min Act: -0.0000

Data Index: 93635 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0086. Min Act: -0.0001

Data Index: 251514 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0086. Min Act: -0.0000

Data Index: 741308 (The Pile)

Max Activating Token Index: 1009

Text #5

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0085. Min Act: -0.0000

Data Index: 136331 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0085. Min Act: -0.0000

Data Index: 403743 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0085. Min Act: -0.0000

Data Index: 1940093 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0001

Data Index: 1823473 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0085. Min Act: -0.0000

Data Index: 1276624 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0084. Min Act: -0.0000

Data Index: 1568482 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0084. Min Act: -0.0000

Data Index: 1261743 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0000

Data Index: 1601281 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0000

Data Index: 65449 (The Pile)

Max Activating Token Index: 1018

Text #14

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0000

Data Index: 680975 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0000

Data Index: 1967024 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0085. Min Act: -0.0001

Data Index: 1128283 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0000

Data Index: 449818 (The Pile)

Max Activating Token Index: 1008

Text #18

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0000

Data Index: 760131 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0000

Data Index: 1258426 (The Pile)

Max Activating Token Index: 1023