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

Dataset: The Pile

Neuron 4947 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: 0.5738. Min Range: -0.5738

Max Act: 0.4808. Min Act: -0.0000

Data Index: 1518891 (The Pile)

Max Activating Token Index: 999

Text #1

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1713651 (The Pile)

Max Activating Token Index: 321

Text #2

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4873. Min Act: -0.0000

Data Index: 643655 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4497. Min Act: -0.0000

Data Index: 160947 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4543. Min Act: -0.0000

Data Index: 1829744 (The Pile)

Max Activating Token Index: 316

Text #5

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1852264 (The Pile)

Max Activating Token Index: 217

Text #6

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4396. Min Act: -0.0000

Data Index: 1979727 (The Pile)

Max Activating Token Index: 730

Text #7

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4141. Min Act: -0.0000

Data Index: 547228 (The Pile)

Max Activating Token Index: 70

Text #8

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1092694 (The Pile)

Max Activating Token Index: 402

Text #9

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4084. Min Act: -0.0000

Data Index: 1935282 (The Pile)

Max Activating Token Index: 262

Text #10

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4058. Min Act: -0.0000

Data Index: 564676 (The Pile)

Max Activating Token Index: 762

Text #11

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4037. Min Act: -0.0000

Data Index: 779934 (The Pile)

Max Activating Token Index: 430

Text #12

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4321. Min Act: -0.0000

Data Index: 45415 (The Pile)

Max Activating Token Index: 426

Text #13

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4035. Min Act: -0.0000

Data Index: 919859 (The Pile)

Max Activating Token Index: 402

Text #14

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4166. Min Act: -0.0000

Data Index: 292768 (The Pile)

Max Activating Token Index: 699

Text #15

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4127. Min Act: -0.0000

Data Index: 1882689 (The Pile)

Max Activating Token Index: 836

Text #16

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4011. Min Act: -0.0000

Data Index: 626657 (The Pile)

Max Activating Token Index: 709

Text #17

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4006. Min Act: -0.0000

Data Index: 67229 (The Pile)

Max Activating Token Index: 451

Text #18

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.3934. Min Act: -0.0000

Data Index: 1500794 (The Pile)

Max Activating Token Index: 332

Text #19

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1584487 (The Pile)

Max Activating Token Index: 611