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

Dataset: The Pile

Neuron 146 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: 0.3709. Min Range: -0.3709

Max Act: 0.3709. Min Act: -0.0000

Data Index: 1036258 (The Pile)

Max Activating Token Index: 374

Text #1

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3617. Min Act: -0.0000

Data Index: 760077 (The Pile)

Max Activating Token Index: 648

Text #2

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3191. Min Act: -0.0000

Data Index: 524507 (The Pile)

Max Activating Token Index: 652

Text #3

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3413. Min Act: -0.0000

Data Index: 1992400 (The Pile)

Max Activating Token Index: 224

Text #4

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3170. Min Act: -0.0000

Data Index: 45699 (The Pile)

Max Activating Token Index: 171

Text #5

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2973. Min Act: -0.0000

Data Index: 23008 (The Pile)

Max Activating Token Index: 573

Text #6

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3350. Min Act: -0.0000

Data Index: 627711 (The Pile)

Max Activating Token Index: 426

Text #7

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3295. Min Act: -0.0000

Data Index: 70513 (The Pile)

Max Activating Token Index: 664

Text #8

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3297. Min Act: -0.0000

Data Index: 930884 (The Pile)

Max Activating Token Index: 561

Text #9

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3321. Min Act: -0.0000

Data Index: 793297 (The Pile)

Max Activating Token Index: 383

Text #10

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3284. Min Act: -0.0000

Data Index: 557313 (The Pile)

Max Activating Token Index: 143

Text #11

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1362637 (The Pile)

Max Activating Token Index: 833

Text #12

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1538441 (The Pile)

Max Activating Token Index: 735

Text #13

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3147. Min Act: -0.0000

Data Index: 31900 (The Pile)

Max Activating Token Index: 128

Text #14

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3035. Min Act: -0.0000

Data Index: 372363 (The Pile)

Max Activating Token Index: 819

Text #15

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3299. Min Act: -0.0000

Data Index: 796142 (The Pile)

Max Activating Token Index: 923

Text #16

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3066. Min Act: -0.0000

Data Index: 122127 (The Pile)

Max Activating Token Index: 257

Text #17

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2645. Min Act: -0.0000

Data Index: 1735666 (The Pile)

Max Activating Token Index: 128

Text #18

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2629. Min Act: -0.0000

Data Index: 937837 (The Pile)

Max Activating Token Index: 574

Text #19

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3091. Min Act: -0.0000

Data Index: 327173 (The Pile)

Max Activating Token Index: 13