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

Dataset: The Pile

Neuron 2146 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.3814. Min Act: -0.0000

Data Index: 1292110 (The Pile)

Max Activating Token Index: 689

Text #1

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.2637. Min Act: -0.0000

Data Index: 830828 (The Pile)

Max Activating Token Index: 612

Text #2

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.2271. Min Act: -0.0000

Data Index: 487409 (The Pile)

Max Activating Token Index: 130

Text #3

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.2223. Min Act: -0.0000

Data Index: 1826295 (The Pile)

Max Activating Token Index: 89

Text #4

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.2090. Min Act: -0.0000

Data Index: 902033 (The Pile)

Max Activating Token Index: 13

Text #5

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1782690 (The Pile)

Max Activating Token Index: 301

Text #6

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1348721 (The Pile)

Max Activating Token Index: 641

Text #7

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.1997. Min Act: -0.0000

Data Index: 107677 (The Pile)

Max Activating Token Index: 166

Text #8

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.1601. Min Act: -0.0000

Data Index: 1905446 (The Pile)

Max Activating Token Index: 816

Text #9

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.1782. Min Act: -0.0000

Data Index: 1350031 (The Pile)

Max Activating Token Index: 793

Text #10

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.1651. Min Act: 0.0000

Data Index: 1227710 (The Pile)

Max Activating Token Index: 312

Text #11

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.1868. Min Act: -0.0000

Data Index: 1685980 (The Pile)

Max Activating Token Index: 365

Text #12

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.1800. Min Act: -0.0000

Data Index: 374918 (The Pile)

Max Activating Token Index: 791

Text #13

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.1673. Min Act: -0.0000

Data Index: 130419 (The Pile)

Max Activating Token Index: 986

Text #14

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.1786. Min Act: -0.0000

Data Index: 1266825 (The Pile)

Max Activating Token Index: 371

Text #15

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.1725. Min Act: -0.0000

Data Index: 907280 (The Pile)

Max Activating Token Index: 12

Text #16

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.1627. Min Act: -0.0000

Data Index: 372287 (The Pile)

Max Activating Token Index: 987

Text #17

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.1727. Min Act: 0.0001

Data Index: 347182 (The Pile)

Max Activating Token Index: 187

Text #18

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.1736. Min Act: -0.0000

Data Index: 1454527 (The Pile)

Max Activating Token Index: 548

Text #19

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.1779. Min Act: -0.0000

Data Index: 1845242 (The Pile)

Max Activating Token Index: 33