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

Dataset: The Pile

Neuron 1803 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2639. Min Act: -0.0000

Data Index: 1984723 (The Pile)

Max Activating Token Index: 962

Text #1

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1950. Min Act: -0.0000

Data Index: 58300 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1914. Min Act: -0.0000

Data Index: 267078 (The Pile)

Max Activating Token Index: 1001

Text #3

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1947. Min Act: -0.0000

Data Index: 1942522 (The Pile)

Max Activating Token Index: 132

Text #4

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1136053 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1850. Min Act: -0.0000

Data Index: 135832 (The Pile)

Max Activating Token Index: 562

Text #6

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1896. Min Act: -0.0000

Data Index: 1845969 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1856. Min Act: -0.0000

Data Index: 139461 (The Pile)

Max Activating Token Index: 642

Text #8

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1649. Min Act: -0.0000

Data Index: 1161298 (The Pile)

Max Activating Token Index: 385

Text #9

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1848. Min Act: -0.0000

Data Index: 111451 (The Pile)

Max Activating Token Index: 813

Text #10

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1787. Min Act: -0.0000

Data Index: 1435511 (The Pile)

Max Activating Token Index: 628

Text #11

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1737. Min Act: -0.0000

Data Index: 101525 (The Pile)

Max Activating Token Index: 737

Text #12

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1744. Min Act: -0.0000

Data Index: 419722 (The Pile)

Max Activating Token Index: 455

Text #13

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1742. Min Act: -0.0000

Data Index: 1617896 (The Pile)

Max Activating Token Index: 509

Text #14

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1731. Min Act: -0.0000

Data Index: 895644 (The Pile)

Max Activating Token Index: 673

Text #15

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1839. Min Act: -0.0000

Data Index: 526045 (The Pile)

Max Activating Token Index: 938

Text #16

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1679. Min Act: -0.0000

Data Index: 1675515 (The Pile)

Max Activating Token Index: 347

Text #17

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1664. Min Act: -0.0000

Data Index: 413863 (The Pile)

Max Activating Token Index: 900

Text #18

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1572. Min Act: -0.0000

Data Index: 336938 (The Pile)

Max Activating Token Index: 165

Text #19

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1730. Min Act: -0.0000

Data Index: 247000 (The Pile)

Max Activating Token Index: 155