< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4061 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3878. Min Act: -0.0001

Data Index: 707707 (The Pile)

Max Activating Token Index: 16

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3921. Min Act: -0.0001

Data Index: 1063635 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3889. Min Act: -0.0001

Data Index: 1192155 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3792. Min Act: -0.0001

Data Index: 271808 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3667. Min Act: -0.0001

Data Index: 1298993 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3502. Min Act: -0.0001

Data Index: 919147 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3794. Min Act: -0.0001

Data Index: 1177814 (The Pile)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3768. Min Act: -0.0001

Data Index: 468714 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3541. Min Act: -0.0001

Data Index: 775913 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3485. Min Act: -0.0001

Data Index: 529443 (The Pile)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3925. Min Act: -0.0001

Data Index: 759781 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3658. Min Act: -0.0001

Data Index: 341874 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3908. Min Act: -0.0001

Data Index: 1023631 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3897. Min Act: -0.0001

Data Index: 1611478 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3694. Min Act: -0.0001

Data Index: 601322 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3466. Min Act: -0.0001

Data Index: 309230 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3422. Min Act: -0.0001

Data Index: 365771 (The Pile)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3662. Min Act: -0.0001

Data Index: 546274 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3329. Min Act: -0.0001

Data Index: 607641 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3751. Min Act: -0.0001

Data Index: 673345 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #19