< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.2354. Min Range: -2.2354

Max Act: 2.2354. Min Act: -0.1700

Data Index: 7495336 (The Pile)

Max Activating Token Index: 743

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.2354. Min Range: -2.2354

Max Act: 2.2023. Min Act: -0.1700

Data Index: 9744138 (The Pile)

Max Activating Token Index: 844

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.2354. Min Range: -2.2354

Max Act: 2.1857. Min Act: -0.1700

Data Index: 6745304 (The Pile)

Max Activating Token Index: 901

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.2354. Min Range: -2.2354

Max Act: 2.1857. Min Act: -0.1700

Data Index: 4065867 (The Pile)

Max Activating Token Index: 753

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.2354. Min Range: -2.2354

Max Act: 2.1691. Min Act: -0.1700

Data Index: 9031542 (The Pile)

Max Activating Token Index: 577

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.2354. Min Range: -2.2354

Max Act: 2.1691. Min Act: -0.1700

Data Index: 2892291 (The Pile)

Max Activating Token Index: 678

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.2354. Min Range: -2.2354

Max Act: 2.1691. Min Act: -0.1700

Data Index: 5987140 (The Pile)

Max Activating Token Index: 420

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.2354. Min Range: -2.2354

Max Act: 2.1691. Min Act: -0.1700

Data Index: 5913728 (The Pile)

Max Activating Token Index: 869

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.2354. Min Range: -2.2354

Max Act: 2.1525. Min Act: -0.1700

Data Index: 8367778 (The Pile)

Max Activating Token Index: 670

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.2354. Min Range: -2.2354

Max Act: 2.1525. Min Act: -0.1700

Data Index: 7169734 (The Pile)

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.2354. Min Range: -2.2354

Max Act: 2.1525. Min Act: -0.1700

Data Index: 8123039 (The Pile)

Max Activating Token Index: 215

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.2354. Min Range: -2.2354

Max Act: 2.1525. Min Act: -0.1700

Data Index: 8616100 (The Pile)

Max Activating Token Index: 752

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.2354. Min Range: -2.2354

Max Act: 2.1358. Min Act: -0.1700

Data Index: 2966282 (The Pile)

Max Activating Token Index: 1022

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.2354. Min Range: -2.2354

Max Act: 2.1358. Min Act: -0.1700

Data Index: 9066242 (The Pile)

Max Activating Token Index: 865

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.2354. Min Range: -2.2354

Max Act: 2.1358. Min Act: -0.1700

Data Index: 8061231 (The Pile)

Max Activating Token Index: 920

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.2354. Min Range: -2.2354

Max Act: 2.1358. Min Act: -0.1700

Data Index: 4796620 (The Pile)

Max Activating Token Index: 806

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.2354. Min Range: -2.2354

Max Act: 2.1191. Min Act: -0.1700

Data Index: 5634355 (The Pile)

Max Activating Token Index: 597

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.2354. Min Range: -2.2354

Max Act: 2.1191. Min Act: -0.1700

Data Index: 5885802 (The Pile)

Max Activating Token Index: 752

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.2354. Min Range: -2.2354

Max Act: 2.1191. Min Act: -0.1700

Data Index: 8089535 (The Pile)

Max Activating Token Index: 681

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.2354. Min Range: -2.2354

Max Act: 2.1191. Min Act: -0.1700

Data Index: 9020271 (The Pile)

Max Activating Token Index: 754

Click toggle to see full text

Truncated

Full Text #19