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

Dataset: The Pile

Neuron 110 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: 1.5255. Min Range: -1.5255

Max Act: 1.5255. Min Act: -0.0000

Data Index: 1814043 (The Pile)

Max Activating Token Index: 932

Text #1

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.4442. Min Act: -0.0000

Data Index: 1099939 (The Pile)

Max Activating Token Index: 578

Text #2

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.3318. Min Act: -0.0000

Data Index: 1199150 (The Pile)

Max Activating Token Index: 875

Text #3

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.3228. Min Act: -0.0000

Data Index: 378389 (The Pile)

Max Activating Token Index: 260

Text #4

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.3544. Min Act: -0.0000

Data Index: 688673 (The Pile)

Max Activating Token Index: 472

Text #5

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.3437. Min Act: -0.0000

Data Index: 1694226 (The Pile)

Max Activating Token Index: 961

Text #6

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.3108. Min Act: -0.0000

Data Index: 1490619 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.3165. Min Act: -0.0000

Data Index: 613857 (The Pile)

Max Activating Token Index: 723

Text #8

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.3122. Min Act: -0.0000

Data Index: 854588 (The Pile)

Max Activating Token Index: 524

Text #9

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.2871. Min Act: -0.0000

Data Index: 322689 (The Pile)

Max Activating Token Index: 246

Text #10

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.2999. Min Act: -0.0000

Data Index: 1317333 (The Pile)

Max Activating Token Index: 206

Text #11

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.2856. Min Act: 0.0000

Data Index: 50969 (The Pile)

Max Activating Token Index: 329

Text #12

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.2833. Min Act: -0.0000

Data Index: 286856 (The Pile)

Max Activating Token Index: 627

Text #13

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.2673. Min Act: 0.0000

Data Index: 403407 (The Pile)

Max Activating Token Index: 199

Text #14

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.2393. Min Act: -0.0000

Data Index: 1990444 (The Pile)

Max Activating Token Index: 696

Text #15

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.2644. Min Act: 0.0000

Data Index: 1371039 (The Pile)

Max Activating Token Index: 817

Text #16

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.2169. Min Act: -0.0000

Data Index: 1660947 (The Pile)

Max Activating Token Index: 426

Text #17

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.2199. Min Act: -0.0000

Data Index: 467838 (The Pile)

Max Activating Token Index: 397

Text #18

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.1111. Min Act: -0.0000

Data Index: 329599 (The Pile)

Max Activating Token Index: 971

Text #19

Max Range: 1.5255. Min Range: -1.5255

Max Act: 1.1941. Min Act: -0.0000

Data Index: 382082 (The Pile)

Max Activating Token Index: 326