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

Dataset: The Pile

Neuron 3176 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9046. Min Range: -0.9046

Max Act: 0.9046. Min Act: -0.0000

Data Index: 38988 (The Pile)

Max Activating Token Index: 34

Text #1

Max Range: 0.9046. Min Range: -0.9046

Max Act: 0.7810. Min Act: -0.0000

Data Index: 803924 (The Pile)

Max Activating Token Index: 367

Text #2

Max Range: 0.9046. Min Range: -0.9046

Max Act: 0.7739. Min Act: -0.0000

Data Index: 40987 (The Pile)

Max Activating Token Index: 979

Text #3

Max Range: 0.9046. Min Range: -0.9046

Max Act: 0.7609. Min Act: -0.0000

Data Index: 1237701 (The Pile)

Max Activating Token Index: 869

Text #4

Max Range: 0.9046. Min Range: -0.9046

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1290033 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 0.9046. Min Range: -0.9046

Max Act: 0.7448. Min Act: -0.0000

Data Index: 839524 (The Pile)

Max Activating Token Index: 154

Text #6

Max Range: 0.9046. Min Range: -0.9046

Max Act: 0.8908. Min Act: -0.0000

Data Index: 299677 (The Pile)

Max Activating Token Index: 973

Text #7

Max Range: 0.9046. Min Range: -0.9046

Max Act: 0.7212. Min Act: -0.0000

Data Index: 158208 (The Pile)

Max Activating Token Index: 976

Text #8

Max Range: 0.9046. Min Range: -0.9046

Max Act: 0.7346. Min Act: -0.0000

Data Index: 1591669 (The Pile)

Max Activating Token Index: 563

Text #9

Max Range: 0.9046. Min Range: -0.9046

Max Act: 0.7315. Min Act: -0.0000

Data Index: 1911093 (The Pile)

Max Activating Token Index: 710

Text #10

Max Range: 0.9046. Min Range: -0.9046

Max Act: 0.6729. Min Act: -0.0000

Data Index: 888780 (The Pile)

Max Activating Token Index: 161

Text #11

Max Range: 0.9046. Min Range: -0.9046

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1749002 (The Pile)

Max Activating Token Index: 377

Text #12

Max Range: 0.9046. Min Range: -0.9046

Max Act: 0.6568. Min Act: -0.0000

Data Index: 1961272 (The Pile)

Max Activating Token Index: 223

Text #13

Max Range: 0.9046. Min Range: -0.9046

Max Act: 0.6602. Min Act: -0.0000

Data Index: 784847 (The Pile)

Max Activating Token Index: 409

Text #14

Max Range: 0.9046. Min Range: -0.9046

Max Act: 0.6575. Min Act: -0.0000

Data Index: 967656 (The Pile)

Max Activating Token Index: 505

Text #15

Max Range: 0.9046. Min Range: -0.9046

Max Act: 0.5749. Min Act: -0.0000

Data Index: 712320 (The Pile)

Max Activating Token Index: 587

Text #16

Max Range: 0.9046. Min Range: -0.9046

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1428369 (The Pile)

Max Activating Token Index: 271

Text #17

Max Range: 0.9046. Min Range: -0.9046

Max Act: 0.6401. Min Act: -0.0000

Data Index: 1407667 (The Pile)

Max Activating Token Index: 588

Text #18

Max Range: 0.9046. Min Range: -0.9046

Max Act: 0.7281. Min Act: -0.0000

Data Index: 1796050 (The Pile)

Max Activating Token Index: 964

Text #19

Max Range: 0.9046. Min Range: -0.9046

Max Act: 0.6339. Min Act: -0.0000

Data Index: 58671 (The Pile)

Max Activating Token Index: 294