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

Dataset: The Pile

Neuron 1498 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1839092 (The Pile)

Max Activating Token Index: 879

Text #1

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6537. Min Act: -0.0000

Data Index: 534468 (The Pile)

Max Activating Token Index: 602

Text #2

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1278578 (The Pile)

Max Activating Token Index: 791

Text #3

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.7174. Min Act: -0.0000

Data Index: 1862589 (The Pile)

Max Activating Token Index: 415

Text #4

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6505. Min Act: -0.0000

Data Index: 198454 (The Pile)

Max Activating Token Index: 683

Text #5

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6405. Min Act: -0.0000

Data Index: 485666 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6613. Min Act: -0.0000

Data Index: 878084 (The Pile)

Max Activating Token Index: 319

Text #7

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6734. Min Act: -0.0000

Data Index: 246884 (The Pile)

Max Activating Token Index: 29

Text #8

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6760. Min Act: -0.0000

Data Index: 96978 (The Pile)

Max Activating Token Index: 510

Text #9

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.7722. Min Act: -0.0000

Data Index: 607701 (The Pile)

Max Activating Token Index: 779

Text #10

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.7244. Min Act: -0.0000

Data Index: 1372760 (The Pile)

Max Activating Token Index: 719

Text #11

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6517. Min Act: -0.0000

Data Index: 865884 (The Pile)

Max Activating Token Index: 70

Text #12

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1786260 (The Pile)

Max Activating Token Index: 775

Text #13

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6385. Min Act: -0.0000

Data Index: 207242 (The Pile)

Max Activating Token Index: 576

Text #14

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6367. Min Act: -0.0000

Data Index: 539402 (The Pile)

Max Activating Token Index: 337

Text #15

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1789460 (The Pile)

Max Activating Token Index: 103

Text #16

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1132322 (The Pile)

Max Activating Token Index: 948

Text #17

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1907220 (The Pile)

Max Activating Token Index: 821

Text #18

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6315. Min Act: -0.0000

Data Index: 461496 (The Pile)

Max Activating Token Index: 148

Text #19

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6750. Min Act: -0.0000

Data Index: 163662 (The Pile)

Max Activating Token Index: 924