Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1208 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4444. Min Act: -0.0000

Data Index: 1434572 (The Pile)

Max Activating Token Index: 1019

Text #1

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4508. Min Act: 0.0000

Data Index: 215264 (The Pile)

Max Activating Token Index: 769

Text #2

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1833126 (The Pile)

Max Activating Token Index: 17

Text #3

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4733. Min Act: -0.0000

Data Index: 1648214 (The Pile)

Max Activating Token Index: 980

Text #4

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4574. Min Act: -0.0000

Data Index: 459532 (The Pile)

Max Activating Token Index: 969

Text #5

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3975. Min Act: -0.0000

Data Index: 895622 (The Pile)

Max Activating Token Index: 1019

Text #6

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.4096. Min Act: 0.0000

Data Index: 1258302 (The Pile)

Max Activating Token Index: 900

Text #7

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1445007 (The Pile)

Max Activating Token Index: 821

Text #8

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3895. Min Act: -0.0000

Data Index: 142535 (The Pile)

Max Activating Token Index: 653

Text #9

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3968. Min Act: -0.0000

Data Index: 777386 (The Pile)

Max Activating Token Index: 147

Text #10

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1020002 (The Pile)

Max Activating Token Index: 762

Text #11

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1198163 (The Pile)

Max Activating Token Index: 1019

Text #12

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3635. Min Act: -0.0000

Data Index: 1822652 (The Pile)

Max Activating Token Index: 862

Text #13

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3506. Min Act: -0.0000

Data Index: 488568 (The Pile)

Max Activating Token Index: 813

Text #14

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3688. Min Act: -0.0000

Data Index: 726407 (The Pile)

Max Activating Token Index: 870

Text #15

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3651. Min Act: -0.0000

Data Index: 357336 (The Pile)

Max Activating Token Index: 981

Text #16

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1332200 (The Pile)

Max Activating Token Index: 871

Text #17

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3428. Min Act: -0.0000

Data Index: 1554575 (The Pile)

Max Activating Token Index: 381

Text #18

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3415. Min Act: -0.0000

Data Index: 1651468 (The Pile)

Max Activating Token Index: 337

Text #19

Max Range: 0.4733. Min Range: -0.4733

Max Act: 0.3385. Min Act: -0.0000

Data Index: 923420 (The Pile)

Max Activating Token Index: 529