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

Dataset: The Pile

Neuron 1585 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.7366. Min Act: -0.0000

Data Index: 573415 (The Pile)

Max Activating Token Index: 1002

Text #1

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.9439. Min Act: -0.0000

Data Index: 723878 (The Pile)

Max Activating Token Index: 893

Text #2

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.8639. Min Act: -0.0000

Data Index: 1481301 (The Pile)

Max Activating Token Index: 114

Text #3

Max Range: 4.3266. Min Range: -4.3266

Max Act: 4.3266. Min Act: -0.0000

Data Index: 800960 (The Pile)

Max Activating Token Index: 212

Text #4

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.6795. Min Act: -0.0000

Data Index: 58916 (The Pile)

Max Activating Token Index: 149

Text #5

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.3188. Min Act: -0.0000

Data Index: 121372 (The Pile)

Max Activating Token Index: 958

Text #6

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.7066. Min Act: -0.0000

Data Index: 1780376 (The Pile)

Max Activating Token Index: 1016

Text #7

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.5464. Min Act: -0.0000

Data Index: 396928 (The Pile)

Max Activating Token Index: 380

Text #8

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.4999. Min Act: -0.0000

Data Index: 1590198 (The Pile)

Max Activating Token Index: 1006

Text #9

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.1294. Min Act: -0.0000

Data Index: 1254155 (The Pile)

Max Activating Token Index: 868

Text #10

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.8375. Min Act: -0.0000

Data Index: 957617 (The Pile)

Max Activating Token Index: 925

Text #11

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.6483. Min Act: -0.0000

Data Index: 1391922 (The Pile)

Max Activating Token Index: 968

Text #12

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.3583. Min Act: -0.0000

Data Index: 867709 (The Pile)

Max Activating Token Index: 926

Text #13

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.6095. Min Act: -0.0000

Data Index: 1632296 (The Pile)

Max Activating Token Index: 998

Text #14

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.8962. Min Act: -0.0000

Data Index: 1937658 (The Pile)

Max Activating Token Index: 792

Text #15

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.5255. Min Act: -0.0000

Data Index: 1792202 (The Pile)

Max Activating Token Index: 511

Text #16

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.3154. Min Act: -0.0000

Data Index: 957211 (The Pile)

Max Activating Token Index: 535

Text #17

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.4665. Min Act: -0.0000

Data Index: 1052336 (The Pile)

Max Activating Token Index: 244

Text #18

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.3089. Min Act: -0.0000

Data Index: 1017926 (The Pile)

Max Activating Token Index: 376

Text #19

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.4362. Min Act: -0.0000

Data Index: 1969365 (The Pile)

Max Activating Token Index: 473