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

Dataset: The Pile

Neuron 3970 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.8744. Min Act: -0.0000

Data Index: 899369 (The Pile)

Max Activating Token Index: 765

Text #1

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7694. Min Act: -0.0000

Data Index: 741182 (The Pile)

Max Activating Token Index: 725

Text #2

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7588. Min Act: -0.0000

Data Index: 585700 (The Pile)

Max Activating Token Index: 791

Text #3

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7288. Min Act: -0.0000

Data Index: 492674 (The Pile)

Max Activating Token Index: 204

Text #4

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7111. Min Act: -0.0000

Data Index: 595905 (The Pile)

Max Activating Token Index: 628

Text #5

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7132. Min Act: -0.0000

Data Index: 745520 (The Pile)

Max Activating Token Index: 834

Text #6

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1541520 (The Pile)

Max Activating Token Index: 654

Text #7

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7312. Min Act: -0.0000

Data Index: 556320 (The Pile)

Max Activating Token Index: 446

Text #8

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1923841 (The Pile)

Max Activating Token Index: 718

Text #9

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7202. Min Act: -0.0000

Data Index: 422690 (The Pile)

Max Activating Token Index: 445

Text #10

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1976958 (The Pile)

Max Activating Token Index: 817

Text #11

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1432276 (The Pile)

Max Activating Token Index: 565

Text #12

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1389702 (The Pile)

Max Activating Token Index: 476

Text #13

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6368. Min Act: -0.0000

Data Index: 212053 (The Pile)

Max Activating Token Index: 912

Text #14

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6800. Min Act: -0.0000

Data Index: 1822074 (The Pile)

Max Activating Token Index: 402

Text #15

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6869. Min Act: -0.0000

Data Index: 1689683 (The Pile)

Max Activating Token Index: 895

Text #16

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6276. Min Act: -0.0000

Data Index: 834787 (The Pile)

Max Activating Token Index: 416

Text #17

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6501. Min Act: -0.0000

Data Index: 452270 (The Pile)

Max Activating Token Index: 903

Text #18

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6225. Min Act: -0.0000

Data Index: 556746 (The Pile)

Max Activating Token Index: 893

Text #19

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1896152 (The Pile)

Max Activating Token Index: 500