< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 111 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: 2.7868. Min Range: -2.7868

Max Act: 2.7868. Min Act: -0.1700

Data Index: 4271245 (The Pile)

Max Activating Token Index: 339

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.7868. Min Range: -2.7868

Max Act: 2.7230. Min Act: -0.1700

Data Index: 1373864 (The Pile)

Max Activating Token Index: 697

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.7868. Min Range: -2.7868

Max Act: 2.7230. Min Act: -0.1700

Data Index: 1646025 (The Pile)

Max Activating Token Index: 984

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.7868. Min Range: -2.7868

Max Act: 2.6910. Min Act: -0.1700

Data Index: 10130941 (The Pile)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.7868. Min Range: -2.7868

Max Act: 2.6750. Min Act: -0.1700

Data Index: 10336408 (The Pile)

Max Activating Token Index: 677

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.7868. Min Range: -2.7868

Max Act: 2.6750. Min Act: -0.1700

Data Index: 2420309 (The Pile)

Max Activating Token Index: 1014

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.7868. Min Range: -2.7868

Max Act: 2.6429. Min Act: -0.1700

Data Index: 10402383 (The Pile)

Max Activating Token Index: 585

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.7868. Min Range: -2.7868

Max Act: 2.6910. Min Act: -0.1700

Data Index: 10314401 (The Pile)

Max Activating Token Index: 870

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.7868. Min Range: -2.7868

Max Act: 2.6429. Min Act: -0.1700

Data Index: 9069861 (The Pile)

Max Activating Token Index: 559

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.7868. Min Range: -2.7868

Max Act: 2.6429. Min Act: -0.1700

Data Index: 5779006 (The Pile)

Max Activating Token Index: 895

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.7868. Min Range: -2.7868

Max Act: 2.6750. Min Act: -0.1700

Data Index: 1929241 (The Pile)

Max Activating Token Index: 554

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.7868. Min Range: -2.7868

Max Act: 2.6750. Min Act: -0.1700

Data Index: 8835585 (The Pile)

Max Activating Token Index: 706

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.7868. Min Range: -2.7868

Max Act: 2.6750. Min Act: -0.1700

Data Index: 2706546 (The Pile)

Max Activating Token Index: 535

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.7868. Min Range: -2.7868

Max Act: 2.6429. Min Act: -0.1700

Data Index: 962140 (The Pile)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.7868. Min Range: -2.7868

Max Act: 2.6429. Min Act: -0.1700

Data Index: 2088037 (The Pile)

Max Activating Token Index: 962

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.7868. Min Range: -2.7868

Max Act: 2.6269. Min Act: -0.1700

Data Index: 6042746 (The Pile)

Max Activating Token Index: 307

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.7868. Min Range: -2.7868

Max Act: 2.6750. Min Act: -0.1700

Data Index: 6079506 (The Pile)

Max Activating Token Index: 840

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.7868. Min Range: -2.7868

Max Act: 2.6429. Min Act: -0.1700

Data Index: 9414475 (The Pile)

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.7868. Min Range: -2.7868

Max Act: 2.6429. Min Act: -0.1700

Data Index: 3557056 (The Pile)

Max Activating Token Index: 648

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.7868. Min Range: -2.7868

Max Act: 2.6269. Min Act: -0.1700

Data Index: 3719977 (The Pile)

Max Activating Token Index: 708

Click toggle to see full text

Truncated

Full Text #19