< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.6914. Min Range: -2.6914

Max Act: 2.6754. Min Act: -0.1700

Data Index: 7452911 (The Pile)

Max Activating Token Index: 670

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.6914. Min Range: -2.6914

Max Act: 2.6754. Min Act: -0.1700

Data Index: 781327 (The Pile)

Max Activating Token Index: 507

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.6914. Min Range: -2.6914

Max Act: 2.6914. Min Act: -0.1700

Data Index: 7579710 (The Pile)

Max Activating Token Index: 640

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.6914. Min Range: -2.6914

Max Act: 2.6594. Min Act: -0.1700

Data Index: 6925172 (The Pile)

Max Activating Token Index: 781

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.6914. Min Range: -2.6914

Max Act: 2.6914. Min Act: -0.1700

Data Index: 5206924 (The Pile)

Max Activating Token Index: 697

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.6914. Min Range: -2.6914

Max Act: 2.6273. Min Act: -0.1700

Data Index: 8366167 (The Pile)

Max Activating Token Index: 493

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.6914. Min Range: -2.6914

Max Act: 2.6754. Min Act: -0.1700

Data Index: 6214278 (The Pile)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.6914. Min Range: -2.6914

Max Act: 2.6594. Min Act: -0.1700

Data Index: 3306506 (The Pile)

Max Activating Token Index: 601

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.6914. Min Range: -2.6914

Max Act: 2.6273. Min Act: -0.1700

Data Index: 10356159 (The Pile)

Max Activating Token Index: 873

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.6914. Min Range: -2.6914

Max Act: 2.6594. Min Act: -0.1700

Data Index: 9708853 (The Pile)

Max Activating Token Index: 1018

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.6914. Min Range: -2.6914

Max Act: 2.6433. Min Act: -0.1700

Data Index: 4397643 (The Pile)

Max Activating Token Index: 235

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.6914. Min Range: -2.6914

Max Act: 2.6273. Min Act: -0.1700

Data Index: 8654484 (The Pile)

Max Activating Token Index: 477

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.6914. Min Range: -2.6914

Max Act: 2.6273. Min Act: -0.1700

Data Index: 3725233 (The Pile)

Max Activating Token Index: 946

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.6914. Min Range: -2.6914

Max Act: 2.6594. Min Act: -0.1700

Data Index: 2553164 (The Pile)

Max Activating Token Index: 666

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.6914. Min Range: -2.6914

Max Act: 2.6273. Min Act: -0.1700

Data Index: 5905233 (The Pile)

Max Activating Token Index: 514

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.6914. Min Range: -2.6914

Max Act: 2.6433. Min Act: -0.1700

Data Index: 4897728 (The Pile)

Max Activating Token Index: 685

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.6914. Min Range: -2.6914

Max Act: 2.6433. Min Act: -0.1700

Data Index: 1697396 (The Pile)

Max Activating Token Index: 592

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.6914. Min Range: -2.6914

Max Act: 2.5951. Min Act: -0.1700

Data Index: 648236 (The Pile)

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.6914. Min Range: -2.6914

Max Act: 2.6273. Min Act: -0.1700

Data Index: 1091524 (The Pile)

Max Activating Token Index: 603

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.6914. Min Range: -2.6914

Max Act: 2.6273. Min Act: -0.1700

Data Index: 8169333 (The Pile)

Max Activating Token Index: 844

Click toggle to see full text

Truncated

Full Text #19