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

Dataset: The Pile

Neuron 4088 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: 8.1480. Min Range: -8.1480

Max Act: 8.1480. Min Act: -0.0000

Data Index: 578708 (The Pile)

Max Activating Token Index: 946

Text #1

Max Range: 8.1480. Min Range: -8.1480

Max Act: 7.0900. Min Act: -0.0000

Data Index: 585161 (The Pile)

Max Activating Token Index: 944

Text #2

Max Range: 8.1480. Min Range: -8.1480

Max Act: 6.1334. Min Act: -0.0000

Data Index: 416834 (The Pile)

Max Activating Token Index: 910

Text #3

Max Range: 8.1480. Min Range: -8.1480

Max Act: 6.1975. Min Act: -0.0000

Data Index: 611060 (The Pile)

Max Activating Token Index: 972

Text #4

Max Range: 8.1480. Min Range: -8.1480

Max Act: 5.5323. Min Act: -0.0000

Data Index: 1702330 (The Pile)

Max Activating Token Index: 831

Text #5

Max Range: 8.1480. Min Range: -8.1480

Max Act: 6.1685. Min Act: -0.0000

Data Index: 430829 (The Pile)

Max Activating Token Index: 911

Text #6

Max Range: 8.1480. Min Range: -8.1480

Max Act: 5.5661. Min Act: -0.0000

Data Index: 742564 (The Pile)

Max Activating Token Index: 809

Text #7

Max Range: 8.1480. Min Range: -8.1480

Max Act: 5.4779. Min Act: -0.0000

Data Index: 8040 (The Pile)

Max Activating Token Index: 604

Text #8

Max Range: 8.1480. Min Range: -8.1480

Max Act: 5.2409. Min Act: -0.0000

Data Index: 1993415 (The Pile)

Max Activating Token Index: 922

Text #9

Max Range: 8.1480. Min Range: -8.1480

Max Act: 5.3293. Min Act: -0.0000

Data Index: 1556625 (The Pile)

Max Activating Token Index: 1020

Text #10

Max Range: 8.1480. Min Range: -8.1480

Max Act: 5.1595. Min Act: -0.0000

Data Index: 1593245 (The Pile)

Max Activating Token Index: 948

Text #11

Max Range: 8.1480. Min Range: -8.1480

Max Act: 5.4310. Min Act: -0.0000

Data Index: 745523 (The Pile)

Max Activating Token Index: 225

Text #12

Max Range: 8.1480. Min Range: -8.1480

Max Act: 5.7427. Min Act: -0.0000

Data Index: 289293 (The Pile)

Max Activating Token Index: 674

Text #13

Max Range: 8.1480. Min Range: -8.1480

Max Act: 5.2657. Min Act: -0.0000

Data Index: 1013777 (The Pile)

Max Activating Token Index: 677

Text #14

Max Range: 8.1480. Min Range: -8.1480

Max Act: 5.1568. Min Act: -0.0000

Data Index: 1627348 (The Pile)

Max Activating Token Index: 534

Text #15

Max Range: 8.1480. Min Range: -8.1480

Max Act: 5.0379. Min Act: -0.0000

Data Index: 661889 (The Pile)

Max Activating Token Index: 992

Text #16

Max Range: 8.1480. Min Range: -8.1480

Max Act: 5.0500. Min Act: -0.0000

Data Index: 1928296 (The Pile)

Max Activating Token Index: 783

Text #17

Max Range: 8.1480. Min Range: -8.1480

Max Act: 4.8531. Min Act: -0.0000

Data Index: 1758769 (The Pile)

Max Activating Token Index: 982

Text #18

Max Range: 8.1480. Min Range: -8.1480

Max Act: 4.3118. Min Act: -0.0000

Data Index: 1699726 (The Pile)

Max Activating Token Index: 1000

Text #19

Max Range: 8.1480. Min Range: -8.1480

Max Act: 4.9717. Min Act: -0.0000

Data Index: 1436450 (The Pile)

Max Activating Token Index: 722