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

Dataset: The Pile

Neuron 2085 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: 1.1503. Min Range: -1.1503

Max Act: 1.1503. Min Act: -0.0000

Data Index: 1585169 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 1.1503. Min Range: -1.1503

Max Act: 1.0208. Min Act: -0.0000

Data Index: 598783 (The Pile)

Max Activating Token Index: 154

Text #2

Max Range: 1.1503. Min Range: -1.1503

Max Act: 1.0391. Min Act: -0.0000

Data Index: 431365 (The Pile)

Max Activating Token Index: 182

Text #3

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9021. Min Act: -0.0000

Data Index: 668460 (The Pile)

Max Activating Token Index: 180

Text #4

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9767. Min Act: 0.0000

Data Index: 533419 (The Pile)

Max Activating Token Index: 40

Text #5

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9772. Min Act: -0.0000

Data Index: 1808675 (The Pile)

Max Activating Token Index: 139

Text #6

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9012. Min Act: -0.0000

Data Index: 1430668 (The Pile)

Max Activating Token Index: 89

Text #7

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9820. Min Act: -0.0000

Data Index: 614989 (The Pile)

Max Activating Token Index: 813

Text #8

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9466. Min Act: -0.0000

Data Index: 979575 (The Pile)

Max Activating Token Index: 168

Text #9

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9314. Min Act: -0.0000

Data Index: 619373 (The Pile)

Max Activating Token Index: 528

Text #10

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.8868. Min Act: -0.0000

Data Index: 822775 (The Pile)

Max Activating Token Index: 132

Text #11

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9334. Min Act: -0.0000

Data Index: 499421 (The Pile)

Max Activating Token Index: 304

Text #12

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9782. Min Act: -0.0000

Data Index: 291884 (The Pile)

Max Activating Token Index: 808

Text #13

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.8671. Min Act: -0.0000

Data Index: 79994 (The Pile)

Max Activating Token Index: 94

Text #14

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9582. Min Act: -0.0000

Data Index: 21755 (The Pile)

Max Activating Token Index: 381

Text #15

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9059. Min Act: -0.0000

Data Index: 1072023 (The Pile)

Max Activating Token Index: 227

Text #16

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.8274. Min Act: -0.0000

Data Index: 492947 (The Pile)

Max Activating Token Index: 191

Text #17

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9209. Min Act: -0.0000

Data Index: 1315803 (The Pile)

Max Activating Token Index: 466

Text #18

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.8864. Min Act: -0.0000

Data Index: 1658491 (The Pile)

Max Activating Token Index: 382

Text #19

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9032. Min Act: -0.0000

Data Index: 1299076 (The Pile)

Max Activating Token Index: 217