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

Dataset: The Pile

Neuron 3560 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.6518. Min Act: -0.0000

Data Index: 810438 (The Pile)

Max Activating Token Index: 948

Text #1

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.5176. Min Act: -0.0000

Data Index: 347060 (The Pile)

Max Activating Token Index: 1004

Text #2

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.3646. Min Act: -0.0000

Data Index: 1201738 (The Pile)

Max Activating Token Index: 983

Text #3

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.3786. Min Act: -0.0000

Data Index: 569856 (The Pile)

Max Activating Token Index: 629

Text #4

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1078295 (The Pile)

Max Activating Token Index: 308

Text #5

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.3564. Min Act: -0.0000

Data Index: 1029430 (The Pile)

Max Activating Token Index: 533

Text #6

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.3587. Min Act: -0.0000

Data Index: 446242 (The Pile)

Max Activating Token Index: 73

Text #7

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.3439. Min Act: -0.0000

Data Index: 224149 (The Pile)

Max Activating Token Index: 472

Text #8

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.3339. Min Act: -0.0000

Data Index: 634658 (The Pile)

Max Activating Token Index: 967

Text #9

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.3434. Min Act: -0.0000

Data Index: 1533826 (The Pile)

Max Activating Token Index: 628

Text #10

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.4023. Min Act: 0.0000

Data Index: 1100125 (The Pile)

Max Activating Token Index: 936

Text #11

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.3513. Min Act: -0.0000

Data Index: 1114176 (The Pile)

Max Activating Token Index: 985

Text #12

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.3398. Min Act: -0.0000

Data Index: 1534118 (The Pile)

Max Activating Token Index: 174

Text #13

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1428552 (The Pile)

Max Activating Token Index: 500

Text #14

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.3563. Min Act: -0.0000

Data Index: 132867 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.3570. Min Act: -0.0000

Data Index: 436399 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.3936. Min Act: -0.0000

Data Index: 774013 (The Pile)

Max Activating Token Index: 76

Text #17

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.3709. Min Act: -0.0000

Data Index: 1513281 (The Pile)

Max Activating Token Index: 557

Text #18

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.3720. Min Act: -0.0000

Data Index: 1374038 (The Pile)

Max Activating Token Index: 568

Text #19

Max Range: 0.6518. Min Range: -0.6518

Max Act: 0.3456. Min Act: -0.0000

Data Index: 609926 (The Pile)

Max Activating Token Index: 485