< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 37 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: 2.3794. Min Range: -2.3794

Max Act: 2.3794. Min Act: -0.1700

Data Index: 1421743 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.3794. Min Range: -2.3794

Max Act: 2.3631. Min Act: -0.1700

Data Index: 2918228 (The Pile)

Max Activating Token Index: 166

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.3794. Min Range: -2.3794

Max Act: 2.3631. Min Act: -0.1700

Data Index: 484896 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.3794. Min Range: -2.3794

Max Act: 2.3467. Min Act: -0.1700

Data Index: 4242629 (The Pile)

Max Activating Token Index: 144

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.3794. Min Range: -2.3794

Max Act: 2.3467. Min Act: -0.1700

Data Index: 8366767 (The Pile)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.3794. Min Range: -2.3794

Max Act: 2.3303. Min Act: -0.1700

Data Index: 7770086 (The Pile)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.3794. Min Range: -2.3794

Max Act: 2.3303. Min Act: -0.1700

Data Index: 7077217 (The Pile)

Max Activating Token Index: 52

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.3794. Min Range: -2.3794

Max Act: 2.3303. Min Act: -0.1700

Data Index: 394286 (The Pile)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.3794. Min Range: -2.3794

Max Act: 2.3139. Min Act: -0.1700

Data Index: 7791511 (The Pile)

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.3794. Min Range: -2.3794

Max Act: 2.3139. Min Act: -0.1700

Data Index: 9269891 (The Pile)

Max Activating Token Index: 174

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.3794. Min Range: -2.3794

Max Act: 2.3139. Min Act: -0.1700

Data Index: 3449618 (The Pile)

Max Activating Token Index: 654

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.3794. Min Range: -2.3794

Max Act: 2.3139. Min Act: -0.1700

Data Index: 6534401 (The Pile)

Max Activating Token Index: 627

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.3794. Min Range: -2.3794

Max Act: 2.3139. Min Act: -0.1700

Data Index: 2363310 (The Pile)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.3794. Min Range: -2.3794

Max Act: 2.3139. Min Act: -0.1700

Data Index: 6153992 (The Pile)

Max Activating Token Index: 270

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.3794. Min Range: -2.3794

Max Act: 2.2975. Min Act: -0.1700

Data Index: 8314875 (The Pile)

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.3794. Min Range: -2.3794

Max Act: 2.2975. Min Act: -0.1700

Data Index: 7767856 (The Pile)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.3794. Min Range: -2.3794

Max Act: 2.2975. Min Act: -0.1700

Data Index: 4616058 (The Pile)

Max Activating Token Index: 241

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.3794. Min Range: -2.3794

Max Act: 2.2975. Min Act: -0.1700

Data Index: 8401931 (The Pile)

Max Activating Token Index: 975

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.3794. Min Range: -2.3794

Max Act: 2.2975. Min Act: -0.1700

Data Index: 6205465 (The Pile)

Max Activating Token Index: 239

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.3794. Min Range: -2.3794

Max Act: 2.2975. Min Act: -0.1700

Data Index: 8758413 (The Pile)

Max Activating Token Index: 661

Click toggle to see full text

Truncated

Full Text #19