< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4060 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.0351. Min Range: -4.0351

Max Act: 4.0351. Min Act: -0.1700

Data Index: 2465263 (The Pile)

Max Activating Token Index: 904

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.9413. Min Act: -0.1700

Data Index: 7407081 (The Pile)

Max Activating Token Index: 94

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.8475. Min Act: -0.1700

Data Index: 7649360 (The Pile)

Max Activating Token Index: 617

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.7849. Min Act: -0.1700

Data Index: 4060093 (The Pile)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.7693. Min Act: -0.1700

Data Index: 3890995 (The Pile)

Max Activating Token Index: 410

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.7536. Min Act: -0.1700

Data Index: 8178582 (The Pile)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.7536. Min Act: -0.1700

Data Index: 595589 (The Pile)

Max Activating Token Index: 744

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.7380. Min Act: -0.1700

Data Index: 6045821 (The Pile)

Max Activating Token Index: 750

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.7223. Min Act: -0.1700

Data Index: 820524 (The Pile)

Max Activating Token Index: 385

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.7223. Min Act: -0.1700

Data Index: 336295 (The Pile)

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.7223. Min Act: -0.1700

Data Index: 9840074 (The Pile)

Max Activating Token Index: 501

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.7223. Min Act: -0.1700

Data Index: 1685957 (The Pile)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.7067. Min Act: -0.1700

Data Index: 3225282 (The Pile)

Max Activating Token Index: 306

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.7067. Min Act: -0.1700

Data Index: 4647332 (The Pile)

Max Activating Token Index: 475

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.7067. Min Act: -0.1700

Data Index: 887281 (The Pile)

Max Activating Token Index: 641

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.6911. Min Act: -0.1700

Data Index: 6177793 (The Pile)

Max Activating Token Index: 511

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.6911. Min Act: -0.1700

Data Index: 6519621 (The Pile)

Max Activating Token Index: 916

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.6911. Min Act: -0.1700

Data Index: 3003579 (The Pile)

Max Activating Token Index: 904

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.6754. Min Act: -0.1700

Data Index: 9598165 (The Pile)

Max Activating Token Index: 732

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.0351. Min Range: -4.0351

Max Act: 3.6598. Min Act: -0.1700

Data Index: 1374675 (The Pile)

Max Activating Token Index: 685

Click toggle to see full text

Truncated

Full Text #19