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

Dataset: The Pile

Neuron 3905 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1988. Min Range: -1.1988

Max Act: 1.1988. Min Act: -0.0000

Data Index: 250947 (The Pile)

Max Activating Token Index: 42

Text #1

Max Range: 1.1988. Min Range: -1.1988

Max Act: 1.0944. Min Act: -0.0000

Data Index: 1916323 (The Pile)

Max Activating Token Index: 839

Text #2

Max Range: 1.1988. Min Range: -1.1988

Max Act: 1.0405. Min Act: -0.0000

Data Index: 341727 (The Pile)

Max Activating Token Index: 42

Text #3

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.9801. Min Act: -0.0000

Data Index: 1575416 (The Pile)

Max Activating Token Index: 438

Text #4

Max Range: 1.1988. Min Range: -1.1988

Max Act: 1.0117. Min Act: -0.0000

Data Index: 1304463 (The Pile)

Max Activating Token Index: 33

Text #5

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.9859. Min Act: -0.0000

Data Index: 6517 (The Pile)

Max Activating Token Index: 230

Text #6

Max Range: 1.1988. Min Range: -1.1988

Max Act: 1.0370. Min Act: -0.0000

Data Index: 1928833 (The Pile)

Max Activating Token Index: 77

Text #7

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.9618. Min Act: -0.0000

Data Index: 1789642 (The Pile)

Max Activating Token Index: 303

Text #8

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.9714. Min Act: -0.0000

Data Index: 1368503 (The Pile)

Max Activating Token Index: 414

Text #9

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.9381. Min Act: -0.0000

Data Index: 1468899 (The Pile)

Max Activating Token Index: 11

Text #10

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.9558. Min Act: -0.0000

Data Index: 408627 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.9294. Min Act: -0.0000

Data Index: 1122389 (The Pile)

Max Activating Token Index: 685

Text #12

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.9432. Min Act: -0.0000

Data Index: 1239460 (The Pile)

Max Activating Token Index: 139

Text #13

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.9015. Min Act: -0.0000

Data Index: 1160236 (The Pile)

Max Activating Token Index: 611

Text #14

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.9295. Min Act: -0.0000

Data Index: 1229737 (The Pile)

Max Activating Token Index: 56

Text #15

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.9128. Min Act: -0.0000

Data Index: 1572930 (The Pile)

Max Activating Token Index: 235

Text #16

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.9023. Min Act: -0.0000

Data Index: 1735739 (The Pile)

Max Activating Token Index: 112

Text #17

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1379991 (The Pile)

Max Activating Token Index: 152

Text #18

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.8699. Min Act: -0.0000

Data Index: 272573 (The Pile)

Max Activating Token Index: 636

Text #19

Max Range: 1.1988. Min Range: -1.1988

Max Act: 0.8785. Min Act: -0.0000

Data Index: 1870737 (The Pile)

Max Activating Token Index: 17