< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3071 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.4013. Min Act: -0.0003

Data Index: 1530059 (The Pile)

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3863. Min Act: -0.0003

Data Index: 504301 (The Pile)

Max Activating Token Index: 253

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3953. Min Act: -0.0003

Data Index: 1176891 (The Pile)

Max Activating Token Index: 514

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3882. Min Act: -0.0003

Data Index: 825918 (The Pile)

Max Activating Token Index: 61

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3876. Min Act: -0.0003

Data Index: 7540 (The Pile)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3838. Min Act: -0.0003

Data Index: 1284962 (The Pile)

Max Activating Token Index: 68

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3846. Min Act: -0.0003

Data Index: 1722468 (The Pile)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3842. Min Act: -0.0003

Data Index: 1754503 (The Pile)

Max Activating Token Index: 44

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3693. Min Act: -0.0003

Data Index: 1753295 (The Pile)

Max Activating Token Index: 430

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3886. Min Act: -0.0003

Data Index: 991609 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3628. Min Act: -0.0003

Data Index: 1933639 (The Pile)

Max Activating Token Index: 81

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3719. Min Act: -0.0003

Data Index: 138084 (The Pile)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3824. Min Act: -0.0003

Data Index: 1881240 (The Pile)

Max Activating Token Index: 515

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3684. Min Act: -0.0003

Data Index: 744588 (The Pile)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3670. Min Act: -0.0003

Data Index: 831665 (The Pile)

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3670. Min Act: -0.0003

Data Index: 402968 (The Pile)

Max Activating Token Index: 246

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3667. Min Act: -0.0003

Data Index: 970629 (The Pile)

Max Activating Token Index: 149

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3665. Min Act: -0.0003

Data Index: 1272565 (The Pile)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3553. Min Act: -0.0003

Data Index: 529629 (The Pile)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3543. Min Act: -0.0003

Data Index: 1150332 (The Pile)

Max Activating Token Index: 23

Click toggle to see full text

Truncated

Full Text #19