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

Dataset: The Pile

Neuron 647 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: 1.9903. Min Range: -1.9903

Max Act: 1.9735. Min Act: -0.0000

Data Index: 1707230 (The Pile)

Max Activating Token Index: 938

Text #1

Max Range: 1.9903. Min Range: -1.9903

Max Act: 1.9231. Min Act: -0.0000

Data Index: 563857 (The Pile)

Max Activating Token Index: 470

Text #2

Max Range: 1.9903. Min Range: -1.9903

Max Act: 1.7983. Min Act: -0.0000

Data Index: 1684353 (The Pile)

Max Activating Token Index: 652

Text #3

Max Range: 1.9903. Min Range: -1.9903

Max Act: 1.7738. Min Act: -0.0000

Data Index: 1448331 (The Pile)

Max Activating Token Index: 904

Text #4

Max Range: 1.9903. Min Range: -1.9903

Max Act: 1.7989. Min Act: -0.0000

Data Index: 181662 (The Pile)

Max Activating Token Index: 794

Text #5

Max Range: 1.9903. Min Range: -1.9903

Max Act: 1.8361. Min Act: -0.0000

Data Index: 115900 (The Pile)

Max Activating Token Index: 796

Text #6

Max Range: 1.9903. Min Range: -1.9903

Max Act: 1.8207. Min Act: -0.0000

Data Index: 1091479 (The Pile)

Max Activating Token Index: 306

Text #7

Max Range: 1.9903. Min Range: -1.9903

Max Act: 1.6263. Min Act: -0.0000

Data Index: 1995696 (The Pile)

Max Activating Token Index: 517

Text #8

Max Range: 1.9903. Min Range: -1.9903

Max Act: 1.7941. Min Act: -0.0000

Data Index: 1569300 (The Pile)

Max Activating Token Index: 154

Text #9

Max Range: 1.9903. Min Range: -1.9903

Max Act: 1.6019. Min Act: -0.0000

Data Index: 978695 (The Pile)

Max Activating Token Index: 758

Text #10

Max Range: 1.9903. Min Range: -1.9903

Max Act: 1.9903. Min Act: -0.0000

Data Index: 1143280 (The Pile)

Max Activating Token Index: 660

Text #11

Max Range: 1.9903. Min Range: -1.9903

Max Act: 1.8549. Min Act: -0.0000

Data Index: 1120436 (The Pile)

Max Activating Token Index: 796

Text #12

Max Range: 1.9903. Min Range: -1.9903

Max Act: 1.6277. Min Act: -0.0000

Data Index: 401791 (The Pile)

Max Activating Token Index: 282

Text #13

Max Range: 1.9903. Min Range: -1.9903

Max Act: 1.6749. Min Act: -0.0000

Data Index: 157535 (The Pile)

Max Activating Token Index: 895

Text #14

Max Range: 1.9903. Min Range: -1.9903

Max Act: 1.7305. Min Act: -0.0000

Data Index: 975265 (The Pile)

Max Activating Token Index: 654

Text #15

Max Range: 1.9903. Min Range: -1.9903

Max Act: 1.5387. Min Act: -0.0000

Data Index: 814763 (The Pile)

Max Activating Token Index: 515

Text #16

Max Range: 1.9903. Min Range: -1.9903

Max Act: 1.5978. Min Act: -0.0000

Data Index: 69691 (The Pile)

Max Activating Token Index: 890

Text #17

Max Range: 1.9903. Min Range: -1.9903

Max Act: 1.5844. Min Act: -0.0000

Data Index: 181118 (The Pile)

Max Activating Token Index: 450

Text #18

Max Range: 1.9903. Min Range: -1.9903

Max Act: 1.6019. Min Act: -0.0000

Data Index: 1337985 (The Pile)

Max Activating Token Index: 464

Text #19

Max Range: 1.9903. Min Range: -1.9903

Max Act: 1.5018. Min Act: -0.0000

Data Index: 1062188 (The Pile)

Max Activating Token Index: 756