< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 59 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.6782. Min Range: -1.6782

Max Act: 1.6782. Min Act: -0.1700

Data Index: 2607 (The Pile)

Max Activating Token Index: 207

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.6782. Min Range: -1.6782

Max Act: 1.6782. Min Act: -0.1700

Data Index: 96 (The Pile)

Max Activating Token Index: 592

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.6782. Min Range: -1.6782

Max Act: 1.6782. Min Act: -0.1700

Data Index: 3721 (The Pile)

Max Activating Token Index: 515

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.6782. Min Range: -1.6782

Max Act: 1.6782. Min Act: -0.1700

Data Index: 3638 (The Pile)

Max Activating Token Index: 214

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.6782. Min Range: -1.6782

Max Act: 1.6782. Min Act: -0.1700

Data Index: 3614 (The Pile)

Max Activating Token Index: 861

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.6782. Min Range: -1.6782

Max Act: 1.6782. Min Act: -0.1700

Data Index: 3354 (The Pile)

Max Activating Token Index: 837

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.6782. Min Range: -1.6782

Max Act: 1.6782. Min Act: -0.1700

Data Index: 3112 (The Pile)

Max Activating Token Index: 813

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.6782. Min Range: -1.6782

Max Act: 1.6782. Min Act: -0.1700

Data Index: 2732 (The Pile)

Max Activating Token Index: 520

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.6782. Min Range: -1.6782

Max Act: 1.6782. Min Act: -0.1700

Data Index: 2645 (The Pile)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.6782. Min Range: -1.6782

Max Act: 1.6782. Min Act: -0.1700

Data Index: 2633 (The Pile)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.6782. Min Range: -1.6782

Max Act: 1.6782. Min Act: -0.1700

Data Index: 250 (The Pile)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.6782. Min Range: -1.6782

Max Act: 1.6782. Min Act: -0.1700

Data Index: 2594 (The Pile)

Max Activating Token Index: 546

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.6782. Min Range: -1.6782

Max Act: 1.6782. Min Act: -0.1700

Data Index: 2448 (The Pile)

Max Activating Token Index: 252

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.6782. Min Range: -1.6782

Max Act: 1.6782. Min Act: -0.1700

Data Index: 2297 (The Pile)

Max Activating Token Index: 239

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.6782. Min Range: -1.6782

Max Act: 1.6782. Min Act: -0.1700

Data Index: 2188 (The Pile)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.6782. Min Range: -1.6782

Max Act: 1.6782. Min Act: -0.1700

Data Index: 1920 (The Pile)

Max Activating Token Index: 395

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.6782. Min Range: -1.6782

Max Act: 1.6782. Min Act: -0.1700

Data Index: 1873 (The Pile)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.6782. Min Range: -1.6782

Max Act: 1.6782. Min Act: -0.1700

Data Index: 657 (The Pile)

Max Activating Token Index: 306

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.6782. Min Range: -1.6782

Max Act: 1.6782. Min Act: -0.1700

Data Index: 427 (The Pile)

Max Activating Token Index: 373

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.6782. Min Range: -1.6782

Max Act: 1.6782. Min Act: -0.1700

Data Index: 322 (The Pile)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #19