< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 13 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')



Text #0

Max Range: 3.5579. Min Range: -3.5579

Max Act: 3.5579. Min Act: -0.1700

Data Index: 9113949 (The Pile)

Max Activating Token Index: 869

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.5579. Min Range: -3.5579

Max Act: 3.5579. Min Act: -0.1700

Data Index: 1047358 (The Pile)

Max Activating Token Index: 937

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.5579. Min Range: -3.5579

Max Act: 3.5109. Min Act: -0.1700

Data Index: 829317 (The Pile)

Max Activating Token Index: 307

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.5579. Min Range: -3.5579

Max Act: 3.4796. Min Act: -0.1700

Data Index: 477392 (The Pile)

Max Activating Token Index: 303

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.5579. Min Range: -3.5579

Max Act: 3.4483. Min Act: -0.1700

Data Index: 1815363 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.5579. Min Range: -3.5579

Max Act: 3.4483. Min Act: -0.1700

Data Index: 9528553 (The Pile)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.5579. Min Range: -3.5579

Max Act: 3.4483. Min Act: -0.1700

Data Index: 9112284 (The Pile)

Max Activating Token Index: 412

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.5579. Min Range: -3.5579

Max Act: 3.4483. Min Act: -0.1700

Data Index: 7878298 (The Pile)

Max Activating Token Index: 154

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.5579. Min Range: -3.5579

Max Act: 3.4326. Min Act: -0.1700

Data Index: 3573413 (The Pile)

Max Activating Token Index: 253

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.5579. Min Range: -3.5579

Max Act: 3.4326. Min Act: -0.1700

Data Index: 7856300 (The Pile)

Max Activating Token Index: 676

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.5579. Min Range: -3.5579

Max Act: 3.4169. Min Act: -0.1700

Data Index: 7401036 (The Pile)

Max Activating Token Index: 85

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.5579. Min Range: -3.5579

Max Act: 3.4012. Min Act: -0.1700

Data Index: 9559936 (The Pile)

Max Activating Token Index: 994

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.5579. Min Range: -3.5579

Max Act: 3.3855. Min Act: -0.1700

Data Index: 318011 (The Pile)

Max Activating Token Index: 16

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.5579. Min Range: -3.5579

Max Act: 3.3855. Min Act: -0.1700

Data Index: 4687644 (The Pile)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.5579. Min Range: -3.5579

Max Act: 3.3698. Min Act: -0.1700

Data Index: 3740970 (The Pile)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.5579. Min Range: -3.5579

Max Act: 3.3698. Min Act: -0.1700

Data Index: 6848865 (The Pile)

Max Activating Token Index: 672

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.5579. Min Range: -3.5579

Max Act: 3.3698. Min Act: -0.1700

Data Index: 177802 (The Pile)

Max Activating Token Index: 955

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.5579. Min Range: -3.5579

Max Act: 3.3541. Min Act: -0.1700

Data Index: 3402129 (The Pile)

Max Activating Token Index: 867

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.5579. Min Range: -3.5579

Max Act: 3.3384. Min Act: -0.1700

Data Index: 5458514 (The Pile)

Max Activating Token Index: 670

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.5579. Min Range: -3.5579

Max Act: 3.3384. Min Act: -0.1700

Data Index: 901063 (The Pile)

Max Activating Token Index: 280

Click toggle to see full text

Truncated

Full Text #19