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

Dataset: The Pile

Neuron 1661 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: 0.8730. Min Range: -0.8730

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1561369 (The Pile)

Max Activating Token Index: 972

Text #1

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.8730. Min Act: -0.0000

Data Index: 608325 (The Pile)

Max Activating Token Index: 330

Text #2

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7682. Min Act: -0.0000

Data Index: 451929 (The Pile)

Max Activating Token Index: 722

Text #3

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7453. Min Act: -0.0000

Data Index: 1737516 (The Pile)

Max Activating Token Index: 577

Text #4

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.6782. Min Act: -0.0000

Data Index: 1208388 (The Pile)

Max Activating Token Index: 914

Text #5

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.6902. Min Act: -0.0000

Data Index: 1129773 (The Pile)

Max Activating Token Index: 670

Text #6

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.6673. Min Act: -0.0000

Data Index: 744499 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1247857 (The Pile)

Max Activating Token Index: 339

Text #8

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1785849 (The Pile)

Max Activating Token Index: 679

Text #9

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.5814. Min Act: -0.0000

Data Index: 1619594 (The Pile)

Max Activating Token Index: 472

Text #10

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.5520. Min Act: -0.0000

Data Index: 1112626 (The Pile)

Max Activating Token Index: 799

Text #11

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.5939. Min Act: -0.0000

Data Index: 1336453 (The Pile)

Max Activating Token Index: 584

Text #12

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.5690. Min Act: -0.0000

Data Index: 922087 (The Pile)

Max Activating Token Index: 928

Text #13

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.5655. Min Act: -0.0000

Data Index: 1399424 (The Pile)

Max Activating Token Index: 945

Text #14

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.5402. Min Act: -0.0000

Data Index: 1263096 (The Pile)

Max Activating Token Index: 641

Text #15

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.6111. Min Act: -0.0000

Data Index: 1995153 (The Pile)

Max Activating Token Index: 903

Text #16

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1653251 (The Pile)

Max Activating Token Index: 649

Text #17

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.5111. Min Act: -0.0000

Data Index: 822805 (The Pile)

Max Activating Token Index: 962

Text #18

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.5234. Min Act: -0.0000

Data Index: 731824 (The Pile)

Max Activating Token Index: 647

Text #19

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1756444 (The Pile)

Max Activating Token Index: 983