< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 16 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 3.0477. Min Range: -3.0477

Max Act: 3.0477. Min Act: -0.1700

Data Index: 2859722 (The Pile)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.0477. Min Range: -3.0477

Max Act: 3.0003. Min Act: -0.1700

Data Index: 3451938 (The Pile)

Max Activating Token Index: 416

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.0477. Min Range: -3.0477

Max Act: 3.0003. Min Act: -0.1700

Data Index: 1388692 (The Pile)

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.0477. Min Range: -3.0477

Max Act: 2.9845. Min Act: -0.1700

Data Index: 1761765 (The Pile)

Max Activating Token Index: 978

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.0477. Min Range: -3.0477

Max Act: 2.9845. Min Act: -0.1700

Data Index: 5829232 (The Pile)

Max Activating Token Index: 474

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.0477. Min Range: -3.0477

Max Act: 2.9686. Min Act: -0.1700

Data Index: 2076418 (The Pile)

Max Activating Token Index: 418

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.0477. Min Range: -3.0477

Max Act: 2.9686. Min Act: -0.1700

Data Index: 1927260 (The Pile)

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.0477. Min Range: -3.0477

Max Act: 2.9528. Min Act: -0.1700

Data Index: 10080346 (The Pile)

Max Activating Token Index: 562

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.0477. Min Range: -3.0477

Max Act: 2.9528. Min Act: -0.1700

Data Index: 3406617 (The Pile)

Max Activating Token Index: 88

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.0477. Min Range: -3.0477

Max Act: 2.9528. Min Act: -0.1700

Data Index: 255670 (The Pile)

Max Activating Token Index: 911

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.0477. Min Range: -3.0477

Max Act: 2.9528. Min Act: -0.1700

Data Index: 6607427 (The Pile)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.0477. Min Range: -3.0477

Max Act: 2.9528. Min Act: -0.1700

Data Index: 5494474 (The Pile)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.0477. Min Range: -3.0477

Max Act: 2.9528. Min Act: -0.1700

Data Index: 5357077 (The Pile)

Max Activating Token Index: 216

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.0477. Min Range: -3.0477

Max Act: 2.9528. Min Act: -0.1700

Data Index: 10766738 (The Pile)

Max Activating Token Index: 864

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.0477. Min Range: -3.0477

Max Act: 2.9370. Min Act: -0.1700

Data Index: 1549372 (The Pile)

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.0477. Min Range: -3.0477

Max Act: 2.9370. Min Act: -0.1700

Data Index: 5013535 (The Pile)

Max Activating Token Index: 59

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.0477. Min Range: -3.0477

Max Act: 2.9370. Min Act: -0.1700

Data Index: 4953448 (The Pile)

Max Activating Token Index: 752

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.0477. Min Range: -3.0477

Max Act: 2.9370. Min Act: -0.1700

Data Index: 7253531 (The Pile)

Max Activating Token Index: 351

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.0477. Min Range: -3.0477

Max Act: 2.9370. Min Act: -0.1700

Data Index: 7845138 (The Pile)

Max Activating Token Index: 610

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.0477. Min Range: -3.0477

Max Act: 2.9370. Min Act: -0.1700

Data Index: 8264400 (The Pile)

Max Activating Token Index: 1014

Click toggle to see full text

Truncated

Full Text #19