Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 431 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2666. Min Act: -0.0000

Data Index: 1590105 (The Pile)

Max Activating Token Index: 160

Text #1

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2522. Min Act: -0.0001

Data Index: 576353 (The Pile)

Max Activating Token Index: 406

Text #2

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2269. Min Act: -0.0000

Data Index: 995076 (The Pile)

Max Activating Token Index: 215

Text #3

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2349. Min Act: -0.0000

Data Index: 711989 (The Pile)

Max Activating Token Index: 172

Text #4

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2171. Min Act: -0.0000

Data Index: 1454842 (The Pile)

Max Activating Token Index: 329

Text #5

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2226. Min Act: -0.0000

Data Index: 839467 (The Pile)

Max Activating Token Index: 656

Text #6

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2135. Min Act: -0.0001

Data Index: 130397 (The Pile)

Max Activating Token Index: 812

Text #7

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1380851 (The Pile)

Max Activating Token Index: 677

Text #8

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2040. Min Act: -0.0000

Data Index: 998483 (The Pile)

Max Activating Token Index: 881

Text #9

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2044. Min Act: -0.0001

Data Index: 1016605 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1782. Min Act: -0.0000

Data Index: 1929555 (The Pile)

Max Activating Token Index: 822

Text #11

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1924. Min Act: -0.0000

Data Index: 693183 (The Pile)

Max Activating Token Index: 627

Text #12

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1893. Min Act: -0.0000

Data Index: 503788 (The Pile)

Max Activating Token Index: 741

Text #13

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1755. Min Act: -0.0000

Data Index: 1376352 (The Pile)

Max Activating Token Index: 849

Text #14

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1937. Min Act: -0.0000

Data Index: 544341 (The Pile)

Max Activating Token Index: 127

Text #15

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1675. Min Act: 0.0001

Data Index: 288490 (The Pile)

Max Activating Token Index: 671

Text #16

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1859. Min Act: -0.0000

Data Index: 1997652 (The Pile)

Max Activating Token Index: 493

Text #17

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1860089 (The Pile)

Max Activating Token Index: 890

Text #18

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1683650 (The Pile)

Max Activating Token Index: 41

Text #19

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1763. Min Act: -0.0000

Data Index: 1547005 (The Pile)

Max Activating Token Index: 182