< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 21 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 6.0056. Min Range: -6.0056

Max Act: 6.0056. Min Act: -0.1700

Data Index: 609762 (The Pile)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.0056. Min Range: -6.0056

Max Act: 5.8493. Min Act: -0.1700

Data Index: 2135492 (The Pile)

Max Activating Token Index: 851

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.0056. Min Range: -6.0056

Max Act: 5.8181. Min Act: -0.1700

Data Index: 3224682 (The Pile)

Max Activating Token Index: 967

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.0056. Min Range: -6.0056

Max Act: 5.8181. Min Act: -0.1700

Data Index: 876933 (The Pile)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.0056. Min Range: -6.0056

Max Act: 5.8181. Min Act: -0.1700

Data Index: 478013 (The Pile)

Max Activating Token Index: 442

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.0056. Min Range: -6.0056

Max Act: 5.7868. Min Act: -0.1700

Data Index: 9313421 (The Pile)

Max Activating Token Index: 199

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.0056. Min Range: -6.0056

Max Act: 5.7868. Min Act: -0.1700

Data Index: 6648888 (The Pile)

Max Activating Token Index: 524

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.0056. Min Range: -6.0056

Max Act: 5.7868. Min Act: -0.1700

Data Index: 1932677 (The Pile)

Max Activating Token Index: 631

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.0056. Min Range: -6.0056

Max Act: 5.7868. Min Act: -0.1700

Data Index: 3962480 (The Pile)

Max Activating Token Index: 271

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.0056. Min Range: -6.0056

Max Act: 5.7868. Min Act: -0.1700

Data Index: 8202034 (The Pile)

Max Activating Token Index: 442

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.0056. Min Range: -6.0056

Max Act: 5.7556. Min Act: -0.1700

Data Index: 3534617 (The Pile)

Max Activating Token Index: 731

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.0056. Min Range: -6.0056

Max Act: 5.7243. Min Act: -0.1700

Data Index: 5408515 (The Pile)

Max Activating Token Index: 696

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.0056. Min Range: -6.0056

Max Act: 5.6931. Min Act: -0.1700

Data Index: 566578 (The Pile)

Max Activating Token Index: 812

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.0056. Min Range: -6.0056

Max Act: 5.6931. Min Act: -0.1700

Data Index: 8390343 (The Pile)

Max Activating Token Index: 543

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.0056. Min Range: -6.0056

Max Act: 5.6931. Min Act: -0.1700

Data Index: 7409009 (The Pile)

Max Activating Token Index: 744

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.0056. Min Range: -6.0056

Max Act: 5.6618. Min Act: -0.1700

Data Index: 6880659 (The Pile)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.0056. Min Range: -6.0056

Max Act: 5.6618. Min Act: -0.1700

Data Index: 5763666 (The Pile)

Max Activating Token Index: 822

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.0056. Min Range: -6.0056

Max Act: 5.6306. Min Act: -0.1700

Data Index: 5285852 (The Pile)

Max Activating Token Index: 931

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.0056. Min Range: -6.0056

Max Act: 5.6306. Min Act: -0.1700

Data Index: 6538568 (The Pile)

Max Activating Token Index: 440

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.0056. Min Range: -6.0056

Max Act: 5.6306. Min Act: -0.1700

Data Index: 551110 (The Pile)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #19