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

Dataset: The Pile

Neuron 2594 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: 0.4486. Min Range: -0.4486

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1916806 (The Pile)

Max Activating Token Index: 159

Text #1

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3895. Min Act: -0.0000

Data Index: 1019827 (The Pile)

Max Activating Token Index: 59

Text #2

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3744. Min Act: -0.0000

Data Index: 1398258 (The Pile)

Max Activating Token Index: 1019

Text #3

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.4085. Min Act: -0.0000

Data Index: 968314 (The Pile)

Max Activating Token Index: 971

Text #4

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3893. Min Act: -0.0000

Data Index: 496770 (The Pile)

Max Activating Token Index: 284

Text #5

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3537. Min Act: -0.0000

Data Index: 1890360 (The Pile)

Max Activating Token Index: 740

Text #6

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3788. Min Act: -0.0000

Data Index: 1302033 (The Pile)

Max Activating Token Index: 1011

Text #7

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3828. Min Act: -0.0000

Data Index: 245544 (The Pile)

Max Activating Token Index: 527

Text #8

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3736. Min Act: -0.0000

Data Index: 1811563 (The Pile)

Max Activating Token Index: 587

Text #9

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3812. Min Act: -0.0000

Data Index: 469579 (The Pile)

Max Activating Token Index: 881

Text #10

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3996. Min Act: -0.0000

Data Index: 1185696 (The Pile)

Max Activating Token Index: 514

Text #11

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3699. Min Act: -0.0000

Data Index: 317653 (The Pile)

Max Activating Token Index: 348

Text #12

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3753. Min Act: -0.0000

Data Index: 833813 (The Pile)

Max Activating Token Index: 174

Text #13

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3366. Min Act: -0.0000

Data Index: 1110937 (The Pile)

Max Activating Token Index: 121

Text #14

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3754. Min Act: -0.0000

Data Index: 140036 (The Pile)

Max Activating Token Index: 825

Text #15

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3656. Min Act: -0.0000

Data Index: 1950471 (The Pile)

Max Activating Token Index: 969

Text #16

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3628. Min Act: -0.0000

Data Index: 582037 (The Pile)

Max Activating Token Index: 611

Text #17

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3603. Min Act: -0.0000

Data Index: 916725 (The Pile)

Max Activating Token Index: 481

Text #18

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1697080 (The Pile)

Max Activating Token Index: 73

Text #19

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3656. Min Act: -0.0000

Data Index: 18524 (The Pile)

Max Activating Token Index: 803