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

Dataset: The Pile

Neuron 3558 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0810. Min Range: -1.0810

Max Act: 1.0556. Min Act: -0.0000

Data Index: 831046 (The Pile)

Max Activating Token Index: 601

Text #1

Max Range: 1.0810. Min Range: -1.0810

Max Act: 1.0810. Min Act: -0.0000

Data Index: 1079981 (The Pile)

Max Activating Token Index: 688

Text #2

Max Range: 1.0810. Min Range: -1.0810

Max Act: 1.0319. Min Act: -0.0000

Data Index: 1849759 (The Pile)

Max Activating Token Index: 499

Text #3

Max Range: 1.0810. Min Range: -1.0810

Max Act: 1.0227. Min Act: -0.0000

Data Index: 256491 (The Pile)

Max Activating Token Index: 156

Text #4

Max Range: 1.0810. Min Range: -1.0810

Max Act: 1.0171. Min Act: -0.0000

Data Index: 664620 (The Pile)

Max Activating Token Index: 170

Text #5

Max Range: 1.0810. Min Range: -1.0810

Max Act: 1.0085. Min Act: -0.0000

Data Index: 1667496 (The Pile)

Max Activating Token Index: 443

Text #6

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9891. Min Act: -0.0000

Data Index: 1876175 (The Pile)

Max Activating Token Index: 514

Text #7

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9702. Min Act: -0.0000

Data Index: 723704 (The Pile)

Max Activating Token Index: 497

Text #8

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1250916 (The Pile)

Max Activating Token Index: 24

Text #9

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.8937. Min Act: -0.0000

Data Index: 365277 (The Pile)

Max Activating Token Index: 545

Text #10

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9367. Min Act: -0.0000

Data Index: 208953 (The Pile)

Max Activating Token Index: 623

Text #11

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1990383 (The Pile)

Max Activating Token Index: 962

Text #12

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1229979 (The Pile)

Max Activating Token Index: 89

Text #13

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9915. Min Act: -0.0000

Data Index: 216167 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9285. Min Act: -0.0000

Data Index: 986282 (The Pile)

Max Activating Token Index: 903

Text #15

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1754987 (The Pile)

Max Activating Token Index: 846

Text #16

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.8630. Min Act: -0.0000

Data Index: 570260 (The Pile)

Max Activating Token Index: 397

Text #17

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9641. Min Act: -0.0000

Data Index: 137768 (The Pile)

Max Activating Token Index: 486

Text #18

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1594392 (The Pile)

Max Activating Token Index: 190

Text #19

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9538. Min Act: -0.0000

Data Index: 1855644 (The Pile)

Max Activating Token Index: 778