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

Dataset: The Pile

Neuron 142 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: 0.5280. Min Range: -0.5280

Max Act: 0.5280. Min Act: -0.0000

Data Index: 767205 (The Pile)

Max Activating Token Index: 535

Text #1

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4418. Min Act: -0.0000

Data Index: 574874 (The Pile)

Max Activating Token Index: 543

Text #2

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4111. Min Act: -0.0000

Data Index: 908820 (The Pile)

Max Activating Token Index: 254

Text #3

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1918149 (The Pile)

Max Activating Token Index: 714

Text #4

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3836. Min Act: -0.0000

Data Index: 82855 (The Pile)

Max Activating Token Index: 759

Text #5

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1187812 (The Pile)

Max Activating Token Index: 812

Text #6

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3699. Min Act: -0.0000

Data Index: 1141061 (The Pile)

Max Activating Token Index: 904

Text #7

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3468. Min Act: -0.0000

Data Index: 842734 (The Pile)

Max Activating Token Index: 530

Text #8

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1486400 (The Pile)

Max Activating Token Index: 925

Text #9

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3279. Min Act: -0.0000

Data Index: 1003280 (The Pile)

Max Activating Token Index: 206

Text #10

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3354. Min Act: -0.0000

Data Index: 136922 (The Pile)

Max Activating Token Index: 496

Text #11

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3154. Min Act: -0.0000

Data Index: 1389430 (The Pile)

Max Activating Token Index: 543

Text #12

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3216. Min Act: -0.0000

Data Index: 1905303 (The Pile)

Max Activating Token Index: 123

Text #13

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3283. Min Act: -0.0000

Data Index: 1870562 (The Pile)

Max Activating Token Index: 617

Text #14

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.2953. Min Act: -0.0000

Data Index: 1334707 (The Pile)

Max Activating Token Index: 234

Text #15

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3227. Min Act: -0.0000

Data Index: 664135 (The Pile)

Max Activating Token Index: 192

Text #16

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1762109 (The Pile)

Max Activating Token Index: 37

Text #17

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3009. Min Act: -0.0000

Data Index: 999812 (The Pile)

Max Activating Token Index: 344

Text #18

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.2925. Min Act: -0.0000

Data Index: 326264 (The Pile)

Max Activating Token Index: 37

Text #19

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1238782 (The Pile)

Max Activating Token Index: 875