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

Dataset: The Pile

Neuron 2617 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0568. Min Range: -1.0568

Max Act: 1.0174. Min Act: -0.0000

Data Index: 846437 (The Pile)

Max Activating Token Index: 911

Text #1

Max Range: 1.0568. Min Range: -1.0568

Max Act: 1.0568. Min Act: -0.0000

Data Index: 1953340 (The Pile)

Max Activating Token Index: 1015

Text #2

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.8467. Min Act: -0.0000

Data Index: 606363 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7948. Min Act: -0.0000

Data Index: 33309 (The Pile)

Max Activating Token Index: 700

Text #4

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.8387. Min Act: -0.0000

Data Index: 896984 (The Pile)

Max Activating Token Index: 870

Text #5

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.8301. Min Act: -0.0000

Data Index: 917809 (The Pile)

Max Activating Token Index: 72

Text #6

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7756. Min Act: -0.0000

Data Index: 558476 (The Pile)

Max Activating Token Index: 637

Text #7

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7987. Min Act: -0.0000

Data Index: 1566716 (The Pile)

Max Activating Token Index: 809

Text #8

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7659. Min Act: -0.0000

Data Index: 1416204 (The Pile)

Max Activating Token Index: 894

Text #9

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7209. Min Act: -0.0000

Data Index: 1236691 (The Pile)

Max Activating Token Index: 1020

Text #10

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7573. Min Act: -0.0000

Data Index: 471453 (The Pile)

Max Activating Token Index: 889

Text #11

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1607631 (The Pile)

Max Activating Token Index: 667

Text #12

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7278. Min Act: -0.0000

Data Index: 88799 (The Pile)

Max Activating Token Index: 340

Text #13

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7091. Min Act: -0.0000

Data Index: 458682 (The Pile)

Max Activating Token Index: 350

Text #14

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1735051 (The Pile)

Max Activating Token Index: 614

Text #15

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7518. Min Act: -0.0000

Data Index: 185315 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1525611 (The Pile)

Max Activating Token Index: 545

Text #17

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1301321 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.6872. Min Act: -0.0000

Data Index: 436148 (The Pile)

Max Activating Token Index: 238

Text #19

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7322. Min Act: -0.0000

Data Index: 282781 (The Pile)

Max Activating Token Index: 968