< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2003 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.6692. Min Act: -0.1700

Data Index: 4656321 (The Pile)

Max Activating Token Index: 640

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5753. Min Act: -0.1700

Data Index: 5826396 (The Pile)

Max Activating Token Index: 742

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5753. Min Act: -0.1700

Data Index: 8246390 (The Pile)

Max Activating Token Index: 774

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5596. Min Act: -0.1700

Data Index: 3338488 (The Pile)

Max Activating Token Index: 887

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5596. Min Act: -0.1700

Data Index: 8863556 (The Pile)

Max Activating Token Index: 965

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5596. Min Act: -0.1700

Data Index: 1172828 (The Pile)

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5596. Min Act: -0.1700

Data Index: 9403414 (The Pile)

Max Activating Token Index: 44

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5596. Min Act: -0.1700

Data Index: 1445657 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5440. Min Act: -0.1700

Data Index: 6154573 (The Pile)

Max Activating Token Index: 272

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5440. Min Act: -0.1700

Data Index: 9955675 (The Pile)

Max Activating Token Index: 856

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5440. Min Act: -0.1700

Data Index: 9823314 (The Pile)

Max Activating Token Index: 960

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5440. Min Act: -0.1700

Data Index: 8402500 (The Pile)

Max Activating Token Index: 89

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5440. Min Act: -0.1700

Data Index: 5809444 (The Pile)

Max Activating Token Index: 943

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5440. Min Act: -0.1700

Data Index: 2449263 (The Pile)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5283. Min Act: -0.1700

Data Index: 9238114 (The Pile)

Max Activating Token Index: 54

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5283. Min Act: -0.1700

Data Index: 1814119 (The Pile)

Max Activating Token Index: 359

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5283. Min Act: -0.1700

Data Index: 9118224 (The Pile)

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5283. Min Act: -0.1700

Data Index: 5016721 (The Pile)

Max Activating Token Index: 623

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5283. Min Act: -0.1700

Data Index: 2608917 (The Pile)

Max Activating Token Index: 251

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.6692. Min Range: -3.6692

Max Act: 3.5283. Min Act: -0.1700

Data Index: 8424976 (The Pile)

Max Activating Token Index: 601

Click toggle to see full text

Truncated

Full Text #19