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

Dataset: The Pile

Neuron 3543 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: 0.7843. Min Range: -0.7843

Max Act: 0.7843. Min Act: -0.0000

Data Index: 111636 (The Pile)

Max Activating Token Index: 653

Text #1

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6649. Min Act: -0.0000

Data Index: 1162010 (The Pile)

Max Activating Token Index: 491

Text #2

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.7261. Min Act: -0.0000

Data Index: 539698 (The Pile)

Max Activating Token Index: 949

Text #3

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6359. Min Act: -0.0000

Data Index: 331916 (The Pile)

Max Activating Token Index: 407

Text #4

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6013. Min Act: -0.0000

Data Index: 967834 (The Pile)

Max Activating Token Index: 536

Text #5

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5934. Min Act: -0.0000

Data Index: 631790 (The Pile)

Max Activating Token Index: 69

Text #6

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6027. Min Act: -0.0000

Data Index: 1044503 (The Pile)

Max Activating Token Index: 376

Text #7

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5673. Min Act: -0.0000

Data Index: 476264 (The Pile)

Max Activating Token Index: 679

Text #8

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6339. Min Act: -0.0000

Data Index: 950672 (The Pile)

Max Activating Token Index: 903

Text #9

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.6077. Min Act: -0.0000

Data Index: 1182697 (The Pile)

Max Activating Token Index: 363

Text #10

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5442. Min Act: -0.0000

Data Index: 1966789 (The Pile)

Max Activating Token Index: 890

Text #11

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1707841 (The Pile)

Max Activating Token Index: 7

Text #12

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5496. Min Act: -0.0000

Data Index: 700756 (The Pile)

Max Activating Token Index: 632

Text #13

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5431. Min Act: -0.0000

Data Index: 1987938 (The Pile)

Max Activating Token Index: 958

Text #14

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5578. Min Act: -0.0000

Data Index: 1903265 (The Pile)

Max Activating Token Index: 301

Text #15

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5555. Min Act: -0.0000

Data Index: 166435 (The Pile)

Max Activating Token Index: 419

Text #16

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1995530 (The Pile)

Max Activating Token Index: 741

Text #17

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5650. Min Act: -0.0000

Data Index: 1709052 (The Pile)

Max Activating Token Index: 403

Text #18

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1329356 (The Pile)

Max Activating Token Index: 697

Text #19

Max Range: 0.7843. Min Range: -0.7843

Max Act: 0.4943. Min Act: -0.0000

Data Index: 921391 (The Pile)

Max Activating Token Index: 959