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

Dataset: The Pile

Neuron 2558 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7928. Min Act: -0.0000

Data Index: 1194206 (The Pile)

Max Activating Token Index: 829

Text #1

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.8731. Min Act: -0.0000

Data Index: 199521 (The Pile)

Max Activating Token Index: 19

Text #2

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.8263. Min Act: -0.0000

Data Index: 496080 (The Pile)

Max Activating Token Index: 61

Text #3

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6767. Min Act: -0.0000

Data Index: 1598585 (The Pile)

Max Activating Token Index: 928

Text #4

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7598. Min Act: -0.0000

Data Index: 1981187 (The Pile)

Max Activating Token Index: 939

Text #5

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7418. Min Act: -0.0000

Data Index: 1157862 (The Pile)

Max Activating Token Index: 392

Text #6

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1590356 (The Pile)

Max Activating Token Index: 979

Text #7

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7180. Min Act: -0.0000

Data Index: 624023 (The Pile)

Max Activating Token Index: 942

Text #8

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6758. Min Act: -0.0000

Data Index: 442079 (The Pile)

Max Activating Token Index: 446

Text #9

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.5957. Min Act: -0.0000

Data Index: 331355 (The Pile)

Max Activating Token Index: 798

Text #10

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.5918. Min Act: -0.0000

Data Index: 245541 (The Pile)

Max Activating Token Index: 116

Text #11

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6455. Min Act: -0.0000

Data Index: 839318 (The Pile)

Max Activating Token Index: 1013

Text #12

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1273189 (The Pile)

Max Activating Token Index: 656

Text #13

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1971244 (The Pile)

Max Activating Token Index: 554

Text #14

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6420. Min Act: -0.0000

Data Index: 1188898 (The Pile)

Max Activating Token Index: 313

Text #15

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1838286 (The Pile)

Max Activating Token Index: 277

Text #16

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6289. Min Act: -0.0000

Data Index: 334860 (The Pile)

Max Activating Token Index: 101

Text #17

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.5344. Min Act: -0.0000

Data Index: 714416 (The Pile)

Max Activating Token Index: 174

Text #18

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.5712. Min Act: -0.0000

Data Index: 1246773 (The Pile)

Max Activating Token Index: 143

Text #19

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.5757. Min Act: -0.0000

Data Index: 1304035 (The Pile)

Max Activating Token Index: 93