< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2016 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.1700

Data Index: 2512 (The Pile)

Max Activating Token Index: 165

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.1700

Data Index: 3067 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.1700

Data Index: 2801 (The Pile)

Max Activating Token Index: 239

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.1700

Data Index: 506 (The Pile)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.1700

Data Index: 2727 (The Pile)

Max Activating Token Index: 749

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.1700

Data Index: 2624 (The Pile)

Max Activating Token Index: 620

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.1700

Data Index: 2622 (The Pile)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.1700

Data Index: 193 (The Pile)

Max Activating Token Index: 493

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.1700

Data Index: 33 (The Pile)

Max Activating Token Index: 917

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.1700

Data Index: 417 (The Pile)

Max Activating Token Index: 973

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.1700

Data Index: 568 (The Pile)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.1700

Data Index: 2388 (The Pile)

Max Activating Token Index: 436

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.1700

Data Index: 2371 (The Pile)

Max Activating Token Index: 720

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.1700

Data Index: 382 (The Pile)

Max Activating Token Index: 985

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.1700

Data Index: 1990 (The Pile)

Max Activating Token Index: 311

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.1700

Data Index: 369 (The Pile)

Max Activating Token Index: 784

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.1700

Data Index: 1573 (The Pile)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.1700

Data Index: 1559 (The Pile)

Max Activating Token Index: 898

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.1700

Data Index: 822 (The Pile)

Max Activating Token Index: 664

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.2950. Min Range: -1.2950

Max Act: 1.2950. Min Act: -0.1700

Data Index: 598 (The Pile)

Max Activating Token Index: 204

Click toggle to see full text

Truncated

Full Text #19