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

Dataset: The Pile

Neuron 3558 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2686. Min Act: -0.0000

Data Index: 1920831 (The Pile)

Max Activating Token Index: 827

Text #1

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1874564 (The Pile)

Max Activating Token Index: 479

Text #2

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2632. Min Act: -0.0000

Data Index: 926426 (The Pile)

Max Activating Token Index: 764

Text #3

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2226. Min Act: -0.0000

Data Index: 391090 (The Pile)

Max Activating Token Index: 208

Text #4

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1815449 (The Pile)

Max Activating Token Index: 1017

Text #5

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2299. Min Act: -0.0000

Data Index: 1697532 (The Pile)

Max Activating Token Index: 566

Text #6

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2202. Min Act: -0.0000

Data Index: 93952 (The Pile)

Max Activating Token Index: 1017

Text #7

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2335. Min Act: -0.0000

Data Index: 540545 (The Pile)

Max Activating Token Index: 563

Text #8

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2195. Min Act: -0.0000

Data Index: 677776 (The Pile)

Max Activating Token Index: 970

Text #9

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2103. Min Act: -0.0000

Data Index: 442153 (The Pile)

Max Activating Token Index: 900

Text #10

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1564427 (The Pile)

Max Activating Token Index: 708

Text #11

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2036. Min Act: -0.0000

Data Index: 947680 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1838. Min Act: -0.0000

Data Index: 1629385 (The Pile)

Max Activating Token Index: 787

Text #13

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1491719 (The Pile)

Max Activating Token Index: 1012

Text #14

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2022. Min Act: -0.0000

Data Index: 1077076 (The Pile)

Max Activating Token Index: 720

Text #15

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2044. Min Act: -0.0000

Data Index: 1845456 (The Pile)

Max Activating Token Index: 1012

Text #16

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1878. Min Act: -0.0000

Data Index: 368202 (The Pile)

Max Activating Token Index: 918

Text #17

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1771. Min Act: -0.0000

Data Index: 681863 (The Pile)

Max Activating Token Index: 602

Text #18

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1640439 (The Pile)

Max Activating Token Index: 422

Text #19

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1639. Min Act: -0.0000

Data Index: 569546 (The Pile)

Max Activating Token Index: 1006