< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4 in Layer 21

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.7620. Min Range: -4.7620

Max Act: 4.7620. Min Act: -0.1700

Data Index: 3015345 (The Pile)

Max Activating Token Index: 508

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.7620. Min Range: -4.7620

Max Act: 4.6682. Min Act: -0.1700

Data Index: 7107619 (The Pile)

Max Activating Token Index: 768

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.7620. Min Range: -4.7620

Max Act: 4.6370. Min Act: -0.1700

Data Index: 5621149 (The Pile)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.7620. Min Range: -4.7620

Max Act: 4.6370. Min Act: -0.1700

Data Index: 9712879 (The Pile)

Max Activating Token Index: 1012

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.7620. Min Range: -4.7620

Max Act: 4.6057. Min Act: -0.1700

Data Index: 385291 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.7620. Min Range: -4.7620

Max Act: 4.5745. Min Act: -0.1699

Data Index: 9338426 (The Pile)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.7620. Min Range: -4.7620

Max Act: 4.5745. Min Act: -0.1700

Data Index: 5413060 (The Pile)

Max Activating Token Index: 478

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.7620. Min Range: -4.7620

Max Act: 4.5745. Min Act: -0.1700

Data Index: 5401743 (The Pile)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.7620. Min Range: -4.7620

Max Act: 4.5745. Min Act: -0.1700

Data Index: 6251716 (The Pile)

Max Activating Token Index: 756

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.7620. Min Range: -4.7620

Max Act: 4.5745. Min Act: -0.1700

Data Index: 9363995 (The Pile)

Max Activating Token Index: 489

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.7620. Min Range: -4.7620

Max Act: 4.5432. Min Act: -0.1700

Data Index: 7558126 (The Pile)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.7620. Min Range: -4.7620

Max Act: 4.5432. Min Act: -0.1700

Data Index: 6017388 (The Pile)

Max Activating Token Index: 744

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.7620. Min Range: -4.7620

Max Act: 4.5432. Min Act: -0.1700

Data Index: 8950580 (The Pile)

Max Activating Token Index: 183

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.7620. Min Range: -4.7620

Max Act: 4.5432. Min Act: -0.1700

Data Index: 9135666 (The Pile)

Max Activating Token Index: 432

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.7620. Min Range: -4.7620

Max Act: 4.5432. Min Act: -0.1699

Data Index: 7072208 (The Pile)

Max Activating Token Index: 860

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.7620. Min Range: -4.7620

Max Act: 4.5432. Min Act: -0.1700

Data Index: 7024954 (The Pile)

Max Activating Token Index: 571

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.7620. Min Range: -4.7620

Max Act: 4.5432. Min Act: -0.1700

Data Index: 6491981 (The Pile)

Max Activating Token Index: 828

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.7620. Min Range: -4.7620

Max Act: 4.5432. Min Act: -0.1700

Data Index: 3723528 (The Pile)

Max Activating Token Index: 961

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.7620. Min Range: -4.7620

Max Act: 4.5120. Min Act: -0.1700

Data Index: 8831529 (The Pile)

Max Activating Token Index: 569

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.7620. Min Range: -4.7620

Max Act: 4.5120. Min Act: -0.1700

Data Index: 3514078 (The Pile)

Max Activating Token Index: 913

Click toggle to see full text

Truncated

Full Text #19