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

Dataset: The Pile

Neuron 3832 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.8413. Min Act: -0.0000

Data Index: 1894136 (The Pile)

Max Activating Token Index: 349

Text #1

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.8270. Min Act: -0.0000

Data Index: 511815 (The Pile)

Max Activating Token Index: 887

Text #2

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1801350 (The Pile)

Max Activating Token Index: 626

Text #3

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.8359. Min Act: -0.0000

Data Index: 124183 (The Pile)

Max Activating Token Index: 756

Text #4

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.8355. Min Act: 0.0000

Data Index: 453829 (The Pile)

Max Activating Token Index: 571

Text #5

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.7951. Min Act: -0.0000

Data Index: 800067 (The Pile)

Max Activating Token Index: 315

Text #6

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.8260. Min Act: -0.0000

Data Index: 508564 (The Pile)

Max Activating Token Index: 124

Text #7

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1232533 (The Pile)

Max Activating Token Index: 714

Text #8

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6565. Min Act: -0.0000

Data Index: 1560320 (The Pile)

Max Activating Token Index: 622

Text #9

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.7030. Min Act: -0.0000

Data Index: 905628 (The Pile)

Max Activating Token Index: 550

Text #10

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1181825 (The Pile)

Max Activating Token Index: 999

Text #11

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6467. Min Act: -0.0000

Data Index: 1654648 (The Pile)

Max Activating Token Index: 644

Text #12

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6520. Min Act: -0.0000

Data Index: 1889515 (The Pile)

Max Activating Token Index: 377

Text #13

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6022. Min Act: -0.0000

Data Index: 226637 (The Pile)

Max Activating Token Index: 164

Text #14

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6636. Min Act: -0.0000

Data Index: 259150 (The Pile)

Max Activating Token Index: 980

Text #15

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6062. Min Act: -0.0000

Data Index: 83627 (The Pile)

Max Activating Token Index: 643

Text #16

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6630. Min Act: -0.0000

Data Index: 568304 (The Pile)

Max Activating Token Index: 559

Text #17

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6425. Min Act: -0.0000

Data Index: 1964117 (The Pile)

Max Activating Token Index: 37

Text #18

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1738831 (The Pile)

Max Activating Token Index: 275

Text #19

Max Range: 0.8413. Min Range: -0.8413

Max Act: 0.6218. Min Act: -0.0000

Data Index: 168743 (The Pile)

Max Activating Token Index: 857