Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 637 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1836515 (The Pile)

Max Activating Token Index: 275

Text #1

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1163133 (The Pile)

Max Activating Token Index: 249

Text #2

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.7859. Min Act: -0.0000

Data Index: 1366623 (The Pile)

Max Activating Token Index: 980

Text #3

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.7077. Min Act: -0.0000

Data Index: 585421 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6750. Min Act: -0.0000

Data Index: 1059624 (The Pile)

Max Activating Token Index: 234

Text #5

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1251878 (The Pile)

Max Activating Token Index: 186

Text #6

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6436. Min Act: -0.0000

Data Index: 174502 (The Pile)

Max Activating Token Index: 786

Text #7

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6407. Min Act: -0.0000

Data Index: 293635 (The Pile)

Max Activating Token Index: 572

Text #8

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6343. Min Act: -0.0000

Data Index: 1278418 (The Pile)

Max Activating Token Index: 1017

Text #9

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6784. Min Act: -0.0000

Data Index: 853301 (The Pile)

Max Activating Token Index: 777

Text #10

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6125. Min Act: -0.0000

Data Index: 1605875 (The Pile)

Max Activating Token Index: 427

Text #11

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6512. Min Act: 0.0000

Data Index: 1382856 (The Pile)

Max Activating Token Index: 610

Text #12

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1788700 (The Pile)

Max Activating Token Index: 48

Text #13

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6698. Min Act: -0.0000

Data Index: 577201 (The Pile)

Max Activating Token Index: 672

Text #14

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6419. Min Act: -0.0000

Data Index: 179064 (The Pile)

Max Activating Token Index: 458

Text #15

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6462. Min Act: -0.0000

Data Index: 1989894 (The Pile)

Max Activating Token Index: 382

Text #16

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1134818 (The Pile)

Max Activating Token Index: 839

Text #17

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1985784 (The Pile)

Max Activating Token Index: 213

Text #18

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6205. Min Act: -0.0000

Data Index: 920709 (The Pile)

Max Activating Token Index: 182

Text #19

Max Range: 0.7859. Min Range: -0.7859

Max Act: 0.6534. Min Act: -0.0000

Data Index: 657159 (The Pile)

Max Activating Token Index: 978