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

Dataset: The Pile

Neuron 2401 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: 3.4975. Min Range: -3.4975

Max Act: 3.4975. Min Act: -0.0000

Data Index: 945272 (The Pile)

Max Activating Token Index: 847

Text #1

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.4479. Min Act: -0.0000

Data Index: 1405816 (The Pile)

Max Activating Token Index: 510

Text #2

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.0841. Min Act: -0.0000

Data Index: 1536571 (The Pile)

Max Activating Token Index: 76

Text #3

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.5028. Min Act: -0.0000

Data Index: 812329 (The Pile)

Max Activating Token Index: 97

Text #4

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.8071. Min Act: -0.0000

Data Index: 403883 (The Pile)

Max Activating Token Index: 347

Text #5

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.8397. Min Act: -0.0000

Data Index: 1420967 (The Pile)

Max Activating Token Index: 979

Text #6

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.5704. Min Act: -0.0000

Data Index: 129579 (The Pile)

Max Activating Token Index: 992

Text #7

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.5809. Min Act: -0.0000

Data Index: 828274 (The Pile)

Max Activating Token Index: 960

Text #8

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.5442. Min Act: -0.0000

Data Index: 475902 (The Pile)

Max Activating Token Index: 594

Text #9

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.4995. Min Act: -0.0000

Data Index: 1526515 (The Pile)

Max Activating Token Index: 186

Text #10

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.5157. Min Act: -0.0000

Data Index: 834182 (The Pile)

Max Activating Token Index: 790

Text #11

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.6122. Min Act: -0.0000

Data Index: 1893790 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.3457. Min Act: -0.0000

Data Index: 492012 (The Pile)

Max Activating Token Index: 430

Text #13

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.1740. Min Act: -0.0000

Data Index: 451184 (The Pile)

Max Activating Token Index: 154

Text #14

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.4015. Min Act: -0.0000

Data Index: 56269 (The Pile)

Max Activating Token Index: 764

Text #15

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.3831. Min Act: -0.0000

Data Index: 1934238 (The Pile)

Max Activating Token Index: 955

Text #16

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.9247. Min Act: -0.0000

Data Index: 1315803 (The Pile)

Max Activating Token Index: 686

Text #17

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.3303. Min Act: -0.0000

Data Index: 1229293 (The Pile)

Max Activating Token Index: 58

Text #18

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.3549. Min Act: -0.0000

Data Index: 420135 (The Pile)

Max Activating Token Index: 325

Text #19

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.3156. Min Act: -0.0000

Data Index: 1975329 (The Pile)

Max Activating Token Index: 416