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

Dataset: The Pile

Neuron 2295 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.8356. Min Act: -0.0000

Data Index: 1636489 (The Pile)

Max Activating Token Index: 170

Text #1

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.8806. Min Act: -0.0000

Data Index: 8858 (The Pile)

Max Activating Token Index: 91

Text #2

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1844019 (The Pile)

Max Activating Token Index: 958

Text #3

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.8281. Min Act: -0.0000

Data Index: 475371 (The Pile)

Max Activating Token Index: 440

Text #4

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.8156. Min Act: -0.0000

Data Index: 875810 (The Pile)

Max Activating Token Index: 534

Text #5

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.7807. Min Act: -0.0000

Data Index: 295546 (The Pile)

Max Activating Token Index: 611

Text #6

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.6709. Min Act: -0.0000

Data Index: 680394 (The Pile)

Max Activating Token Index: 310

Text #7

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1731361 (The Pile)

Max Activating Token Index: 335

Text #8

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.7225. Min Act: -0.0000

Data Index: 492292 (The Pile)

Max Activating Token Index: 927

Text #9

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.6939. Min Act: -0.0000

Data Index: 1244373 (The Pile)

Max Activating Token Index: 107

Text #10

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.6706. Min Act: -0.0000

Data Index: 1538237 (The Pile)

Max Activating Token Index: 736

Text #11

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.6704. Min Act: -0.0000

Data Index: 480031 (The Pile)

Max Activating Token Index: 358

Text #12

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.6597. Min Act: -0.0000

Data Index: 1516600 (The Pile)

Max Activating Token Index: 345

Text #13

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.6614. Min Act: -0.0000

Data Index: 537778 (The Pile)

Max Activating Token Index: 787

Text #14

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.6858. Min Act: -0.0000

Data Index: 536987 (The Pile)

Max Activating Token Index: 661

Text #15

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1554941 (The Pile)

Max Activating Token Index: 640

Text #16

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.6476. Min Act: -0.0000

Data Index: 1292148 (The Pile)

Max Activating Token Index: 9

Text #17

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.6650. Min Act: -0.0000

Data Index: 403456 (The Pile)

Max Activating Token Index: 638

Text #18

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1502156 (The Pile)

Max Activating Token Index: 394

Text #19

Max Range: 0.8806. Min Range: -0.8806

Max Act: 0.6126. Min Act: -0.0000

Data Index: 1004773 (The Pile)

Max Activating Token Index: 32