< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4036 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')



Text #0

Max Range: 3.0563. Min Range: -3.0563

Max Act: 3.0563. Min Act: -0.1700

Data Index: 9913165 (The Pile)

Max Activating Token Index: 937

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.0563. Min Range: -3.0563

Max Act: 3.0405. Min Act: -0.1700

Data Index: 7414212 (The Pile)

Max Activating Token Index: 717

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.0563. Min Range: -3.0563

Max Act: 3.0247. Min Act: -0.1700

Data Index: 6119860 (The Pile)

Max Activating Token Index: 529

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.0563. Min Range: -3.0563

Max Act: 3.0247. Min Act: -0.1700

Data Index: 3641807 (The Pile)

Max Activating Token Index: 452

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.0563. Min Range: -3.0563

Max Act: 3.0247. Min Act: -0.1700

Data Index: 1476149 (The Pile)

Max Activating Token Index: 888

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.0563. Min Range: -3.0563

Max Act: 3.0089. Min Act: -0.1700

Data Index: 10370249 (The Pile)

Max Activating Token Index: 338

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9931. Min Act: -0.1700

Data Index: 8828386 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9931. Min Act: -0.1700

Data Index: 5629968 (The Pile)

Max Activating Token Index: 910

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9931. Min Act: -0.1700

Data Index: 4257746 (The Pile)

Max Activating Token Index: 148

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9931. Min Act: -0.1700

Data Index: 6260676 (The Pile)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9931. Min Act: -0.1700

Data Index: 1871633 (The Pile)

Max Activating Token Index: 54

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9773. Min Act: -0.1700

Data Index: 4968370 (The Pile)

Max Activating Token Index: 630

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9773. Min Act: -0.1700

Data Index: 8091967 (The Pile)

Max Activating Token Index: 939

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9614. Min Act: -0.1700

Data Index: 5808349 (The Pile)

Max Activating Token Index: 493

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9614. Min Act: -0.1700

Data Index: 9946198 (The Pile)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9614. Min Act: -0.1700

Data Index: 6051596 (The Pile)

Max Activating Token Index: 574

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9614. Min Act: -0.1700

Data Index: 1718857 (The Pile)

Max Activating Token Index: 417

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9456. Min Act: -0.1700

Data Index: 6007573 (The Pile)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9456. Min Act: -0.1700

Data Index: 7100132 (The Pile)

Max Activating Token Index: 832

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9456. Min Act: -0.1700

Data Index: 9968138 (The Pile)

Max Activating Token Index: 390

Click toggle to see full text

Truncated

Full Text #19