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

Dataset: The Pile

Neuron 1113 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: 1.7319. Min Range: -1.7319

Max Act: 1.7319. Min Act: -0.0000

Data Index: 1052445 (The Pile)

Max Activating Token Index: 382

Text #1

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.5490. Min Act: -0.0000

Data Index: 1296229 (The Pile)

Max Activating Token Index: 397

Text #2

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.5453. Min Act: -0.0000

Data Index: 685260 (The Pile)

Max Activating Token Index: 256

Text #3

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.6068. Min Act: -0.0000

Data Index: 856041 (The Pile)

Max Activating Token Index: 294

Text #4

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.5115. Min Act: -0.0000

Data Index: 1410849 (The Pile)

Max Activating Token Index: 598

Text #5

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.5152. Min Act: -0.0000

Data Index: 1684929 (The Pile)

Max Activating Token Index: 298

Text #6

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.5130. Min Act: -0.0000

Data Index: 239445 (The Pile)

Max Activating Token Index: 865

Text #7

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.5046. Min Act: -0.0000

Data Index: 1003390 (The Pile)

Max Activating Token Index: 589

Text #8

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.5064. Min Act: -0.0000

Data Index: 1903991 (The Pile)

Max Activating Token Index: 192

Text #9

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.5045. Min Act: -0.0000

Data Index: 1130850 (The Pile)

Max Activating Token Index: 416

Text #10

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.5109. Min Act: -0.0000

Data Index: 585504 (The Pile)

Max Activating Token Index: 798

Text #11

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.4797. Min Act: -0.0000

Data Index: 1918020 (The Pile)

Max Activating Token Index: 445

Text #12

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.3817. Min Act: -0.0000

Data Index: 1312491 (The Pile)

Max Activating Token Index: 63

Text #13

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.4709. Min Act: -0.0000

Data Index: 1193125 (The Pile)

Max Activating Token Index: 205

Text #14

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.4483. Min Act: -0.0000

Data Index: 1668476 (The Pile)

Max Activating Token Index: 476

Text #15

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.4527. Min Act: -0.0000

Data Index: 1807285 (The Pile)

Max Activating Token Index: 712

Text #16

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.3442. Min Act: -0.0000

Data Index: 420906 (The Pile)

Max Activating Token Index: 13

Text #17

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.5099. Min Act: -0.0000

Data Index: 1140963 (The Pile)

Max Activating Token Index: 869

Text #18

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.3951. Min Act: -0.0000

Data Index: 1985623 (The Pile)

Max Activating Token Index: 278

Text #19

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.3594. Min Act: -0.0000

Data Index: 31390 (The Pile)

Max Activating Token Index: 588