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

Dataset: The Pile

Neuron 1027 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: 4.8036. Min Range: -4.8036

Max Act: 4.5587. Min Act: -0.0000

Data Index: 2787 (The Pile)

Max Activating Token Index: 347

Text #1

Max Range: 4.8036. Min Range: -4.8036

Max Act: 4.7925. Min Act: -0.0000

Data Index: 768020 (The Pile)

Max Activating Token Index: 404

Text #2

Max Range: 4.8036. Min Range: -4.8036

Max Act: 4.4417. Min Act: -0.0000

Data Index: 1377629 (The Pile)

Max Activating Token Index: 401

Text #3

Max Range: 4.8036. Min Range: -4.8036

Max Act: 4.8036. Min Act: -0.0000

Data Index: 577506 (The Pile)

Max Activating Token Index: 309

Text #4

Max Range: 4.8036. Min Range: -4.8036

Max Act: 4.1118. Min Act: -0.0000

Data Index: 884745 (The Pile)

Max Activating Token Index: 794

Text #5

Max Range: 4.8036. Min Range: -4.8036

Max Act: 4.2102. Min Act: -0.0000

Data Index: 977019 (The Pile)

Max Activating Token Index: 649

Text #6

Max Range: 4.8036. Min Range: -4.8036

Max Act: 4.4986. Min Act: -0.0000

Data Index: 515188 (The Pile)

Max Activating Token Index: 912

Text #7

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.0649. Min Act: -0.0000

Data Index: 814603 (The Pile)

Max Activating Token Index: 95

Text #8

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.8100. Min Act: -0.0000

Data Index: 1357248 (The Pile)

Max Activating Token Index: 505

Text #9

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.7431. Min Act: -0.0000

Data Index: 396438 (The Pile)

Max Activating Token Index: 350

Text #10

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.6582. Min Act: -0.0000

Data Index: 1866053 (The Pile)

Max Activating Token Index: 569

Text #11

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.7545. Min Act: -0.0000

Data Index: 496302 (The Pile)

Max Activating Token Index: 84

Text #12

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.6579. Min Act: -0.0000

Data Index: 661863 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.3894. Min Act: -0.0000

Data Index: 644094 (The Pile)

Max Activating Token Index: 30

Text #14

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.6941. Min Act: -0.0000

Data Index: 1131120 (The Pile)

Max Activating Token Index: 406

Text #15

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.4354. Min Act: -0.0000

Data Index: 56384 (The Pile)

Max Activating Token Index: 295

Text #16

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.5620. Min Act: -0.0000

Data Index: 577193 (The Pile)

Max Activating Token Index: 83

Text #17

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.8835. Min Act: -0.0000

Data Index: 1620612 (The Pile)

Max Activating Token Index: 42

Text #18

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.3866. Min Act: -0.0000

Data Index: 1138421 (The Pile)

Max Activating Token Index: 600

Text #19

Max Range: 4.8036. Min Range: -4.8036

Max Act: 3.8106. Min Act: -0.0000

Data Index: 912279 (The Pile)

Max Activating Token Index: 220