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

Dataset: The Pile

Neuron 1950 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1124438 (The Pile)

Max Activating Token Index: 534

Text #1

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.4157. Min Act: -0.0000

Data Index: 1578415 (The Pile)

Max Activating Token Index: 122

Text #2

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.4475. Min Act: -0.0000

Data Index: 872815 (The Pile)

Max Activating Token Index: 226

Text #3

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.4071. Min Act: -0.0000

Data Index: 675018 (The Pile)

Max Activating Token Index: 397

Text #4

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3817. Min Act: -0.0000

Data Index: 51135 (The Pile)

Max Activating Token Index: 794

Text #5

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.4050. Min Act: -0.0000

Data Index: 17449 (The Pile)

Max Activating Token Index: 256

Text #6

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3861. Min Act: -0.0000

Data Index: 1389239 (The Pile)

Max Activating Token Index: 879

Text #7

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1393495 (The Pile)

Max Activating Token Index: 776

Text #8

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3732. Min Act: -0.0000

Data Index: 1375848 (The Pile)

Max Activating Token Index: 432

Text #9

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3469. Min Act: -0.0000

Data Index: 1279659 (The Pile)

Max Activating Token Index: 319

Text #10

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1909966 (The Pile)

Max Activating Token Index: 674

Text #11

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3686. Min Act: -0.0000

Data Index: 609025 (The Pile)

Max Activating Token Index: 156

Text #12

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3572. Min Act: -0.0000

Data Index: 1002742 (The Pile)

Max Activating Token Index: 504

Text #13

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3674. Min Act: -0.0000

Data Index: 89868 (The Pile)

Max Activating Token Index: 424

Text #14

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3956. Min Act: -0.0000

Data Index: 1244606 (The Pile)

Max Activating Token Index: 665

Text #15

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3948. Min Act: 0.0000

Data Index: 1675987 (The Pile)

Max Activating Token Index: 586

Text #16

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1358274 (The Pile)

Max Activating Token Index: 668

Text #17

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1558443 (The Pile)

Max Activating Token Index: 443

Text #18

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3594. Min Act: -0.0000

Data Index: 281361 (The Pile)

Max Activating Token Index: 771

Text #19

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3372. Min Act: -0.0000

Data Index: 1845031 (The Pile)

Max Activating Token Index: 654