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

Dataset: The Pile

Neuron 1062 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.9186. Min Act: -0.0000

Data Index: 1622890 (The Pile)

Max Activating Token Index: 797

Text #1

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1280121 (The Pile)

Max Activating Token Index: 955

Text #2

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8635. Min Act: -0.0000

Data Index: 1335952 (The Pile)

Max Activating Token Index: 656

Text #3

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8347. Min Act: -0.0000

Data Index: 1201862 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7733. Min Act: 0.0000

Data Index: 755634 (The Pile)

Max Activating Token Index: 350

Text #5

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7178. Min Act: -0.0000

Data Index: 994563 (The Pile)

Max Activating Token Index: 756

Text #6

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7268. Min Act: 0.0001

Data Index: 1167891 (The Pile)

Max Activating Token Index: 1016

Text #7

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6705. Min Act: 0.0000

Data Index: 616287 (The Pile)

Max Activating Token Index: 121

Text #8

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6841. Min Act: -0.0000

Data Index: 1968631 (The Pile)

Max Activating Token Index: 275

Text #9

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6640. Min Act: -0.0000

Data Index: 675119 (The Pile)

Max Activating Token Index: 729

Text #10

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6624. Min Act: -0.0000

Data Index: 338601 (The Pile)

Max Activating Token Index: 903

Text #11

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6023. Min Act: 0.0000

Data Index: 103024 (The Pile)

Max Activating Token Index: 975

Text #12

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1818345 (The Pile)

Max Activating Token Index: 714

Text #13

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6606. Min Act: -0.0000

Data Index: 470313 (The Pile)

Max Activating Token Index: 227

Text #14

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6785. Min Act: -0.0000

Data Index: 1985642 (The Pile)

Max Activating Token Index: 620

Text #15

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1893204 (The Pile)

Max Activating Token Index: 894

Text #16

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6735. Min Act: 0.0000

Data Index: 1945653 (The Pile)

Max Activating Token Index: 333

Text #17

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.5875. Min Act: -0.0000

Data Index: 602534 (The Pile)

Max Activating Token Index: 559

Text #18

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6399. Min Act: -0.0000

Data Index: 1094042 (The Pile)

Max Activating Token Index: 789

Text #19

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.5916. Min Act: 0.0000

Data Index: 1096967 (The Pile)

Max Activating Token Index: 727