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

Dataset: The Pile

Neuron 1940 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: 0.9313. Min Range: -0.9313

Max Act: 0.9313. Min Act: -0.0000

Data Index: 933349 (The Pile)

Max Activating Token Index: 977

Text #1

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7703. Min Act: -0.0000

Data Index: 928223 (The Pile)

Max Activating Token Index: 563

Text #2

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7604. Min Act: -0.0000

Data Index: 1593568 (The Pile)

Max Activating Token Index: 362

Text #3

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7538. Min Act: -0.0000

Data Index: 1697924 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7319. Min Act: -0.0000

Data Index: 481338 (The Pile)

Max Activating Token Index: 821

Text #5

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7404. Min Act: -0.0000

Data Index: 1640648 (The Pile)

Max Activating Token Index: 111

Text #6

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7500. Min Act: -0.0000

Data Index: 826966 (The Pile)

Max Activating Token Index: 375

Text #7

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1369469 (The Pile)

Max Activating Token Index: 922

Text #8

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.6675. Min Act: -0.0000

Data Index: 1926290 (The Pile)

Max Activating Token Index: 883

Text #9

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.6278. Min Act: -0.0000

Data Index: 881820 (The Pile)

Max Activating Token Index: 636

Text #10

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.6471. Min Act: -0.0000

Data Index: 1585190 (The Pile)

Max Activating Token Index: 231

Text #11

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.6857. Min Act: -0.0000

Data Index: 158219 (The Pile)

Max Activating Token Index: 986

Text #12

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7266. Min Act: -0.0000

Data Index: 823292 (The Pile)

Max Activating Token Index: 220

Text #13

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7043. Min Act: -0.0000

Data Index: 259660 (The Pile)

Max Activating Token Index: 30

Text #14

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.6909. Min Act: -0.0000

Data Index: 971381 (The Pile)

Max Activating Token Index: 489

Text #15

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.6262. Min Act: -0.0000

Data Index: 1617600 (The Pile)

Max Activating Token Index: 1020

Text #16

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1559387 (The Pile)

Max Activating Token Index: 80

Text #17

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.6545. Min Act: -0.0000

Data Index: 957098 (The Pile)

Max Activating Token Index: 30

Text #18

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1887158 (The Pile)

Max Activating Token Index: 655

Text #19

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.6479. Min Act: -0.0000

Data Index: 399338 (The Pile)

Max Activating Token Index: 962