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

Dataset: The Pile

Neuron 2501 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.4036. Min Act: -0.0000

Data Index: 772891 (The Pile)

Max Activating Token Index: 837

Text #1

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1099332 (The Pile)

Max Activating Token Index: 822

Text #2

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3858. Min Act: -0.0000

Data Index: 343384 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3795. Min Act: -0.0000

Data Index: 1736072 (The Pile)

Max Activating Token Index: 723

Text #4

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3811. Min Act: -0.0000

Data Index: 1210869 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1822095 (The Pile)

Max Activating Token Index: 305

Text #6

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3808. Min Act: -0.0000

Data Index: 1174226 (The Pile)

Max Activating Token Index: 180

Text #7

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3671. Min Act: -0.0000

Data Index: 1576218 (The Pile)

Max Activating Token Index: 472

Text #8

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3776. Min Act: -0.0000

Data Index: 1680065 (The Pile)

Max Activating Token Index: 328

Text #9

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3511. Min Act: -0.0000

Data Index: 1377772 (The Pile)

Max Activating Token Index: 273

Text #10

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3642. Min Act: -0.0000

Data Index: 1049992 (The Pile)

Max Activating Token Index: 513

Text #11

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3938. Min Act: -0.0000

Data Index: 912368 (The Pile)

Max Activating Token Index: 716

Text #12

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3689. Min Act: -0.0000

Data Index: 244722 (The Pile)

Max Activating Token Index: 395

Text #13

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1163358 (The Pile)

Max Activating Token Index: 310

Text #14

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3545. Min Act: -0.0000

Data Index: 1534761 (The Pile)

Max Activating Token Index: 356

Text #15

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3591. Min Act: -0.0000

Data Index: 1241099 (The Pile)

Max Activating Token Index: 216

Text #16

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3253. Min Act: -0.0000

Data Index: 1677468 (The Pile)

Max Activating Token Index: 558

Text #17

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3454. Min Act: -0.0000

Data Index: 913598 (The Pile)

Max Activating Token Index: 894

Text #18

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3501. Min Act: -0.0000

Data Index: 1946532 (The Pile)

Max Activating Token Index: 214

Text #19

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3118. Min Act: -0.0000

Data Index: 1714313 (The Pile)

Max Activating Token Index: 854