< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 26 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 4.0866. Min Range: -4.0866

Max Act: 4.0866. Min Act: -0.1700

Data Index: 578039 (The Pile)

Max Activating Token Index: 817

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.0866. Min Range: -4.0866

Max Act: 4.0240. Min Act: -0.1700

Data Index: 5934675 (The Pile)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.0866. Min Range: -4.0866

Max Act: 3.6956. Min Act: -0.1700

Data Index: 2073350 (The Pile)

Max Activating Token Index: 449

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.0866. Min Range: -4.0866

Max Act: 3.6800. Min Act: -0.1700

Data Index: 8786349 (The Pile)

Max Activating Token Index: 957

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.0866. Min Range: -4.0866

Max Act: 3.6330. Min Act: -0.1700

Data Index: 6646281 (The Pile)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.0866. Min Range: -4.0866

Max Act: 3.6174. Min Act: -0.1700

Data Index: 8783757 (The Pile)

Max Activating Token Index: 383

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.0866. Min Range: -4.0866

Max Act: 3.6174. Min Act: -0.1700

Data Index: 3731576 (The Pile)

Max Activating Token Index: 158

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.0866. Min Range: -4.0866

Max Act: 3.6017. Min Act: -0.1700

Data Index: 8832021 (The Pile)

Max Activating Token Index: 827

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.0866. Min Range: -4.0866

Max Act: 3.6017. Min Act: -0.1700

Data Index: 10351099 (The Pile)

Max Activating Token Index: 901

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.0866. Min Range: -4.0866

Max Act: 3.5861. Min Act: -0.1700

Data Index: 7552903 (The Pile)

Max Activating Token Index: 218

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.0866. Min Range: -4.0866

Max Act: 3.5861. Min Act: -0.1700

Data Index: 7572392 (The Pile)

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.0866. Min Range: -4.0866

Max Act: 3.5861. Min Act: -0.1700

Data Index: 8270155 (The Pile)

Max Activating Token Index: 357

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.0866. Min Range: -4.0866

Max Act: 3.5861. Min Act: -0.1700

Data Index: 5010851 (The Pile)

Max Activating Token Index: 540

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.0866. Min Range: -4.0866

Max Act: 3.5704. Min Act: -0.1700

Data Index: 4526204 (The Pile)

Max Activating Token Index: 733

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.0866. Min Range: -4.0866

Max Act: 3.5704. Min Act: -0.1700

Data Index: 1068937 (The Pile)

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.0866. Min Range: -4.0866

Max Act: 3.5547. Min Act: -0.1700

Data Index: 7153142 (The Pile)

Max Activating Token Index: 780

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.0866. Min Range: -4.0866

Max Act: 3.5547. Min Act: -0.1700

Data Index: 7414500 (The Pile)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.0866. Min Range: -4.0866

Max Act: 3.5547. Min Act: -0.1700

Data Index: 9138747 (The Pile)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.0866. Min Range: -4.0866

Max Act: 3.5547. Min Act: -0.1700

Data Index: 7049657 (The Pile)

Max Activating Token Index: 778

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.0866. Min Range: -4.0866

Max Act: 3.5547. Min Act: -0.1700

Data Index: 7658439 (The Pile)

Max Activating Token Index: 682

Click toggle to see full text

Truncated

Full Text #19