< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 70 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.8868. Min Range: -2.8868

Max Act: 2.8868. Min Act: -0.1700

Data Index: 394321 (The Pile)

Max Activating Token Index: 672

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.8868. Min Range: -2.8868

Max Act: 2.8392. Min Act: -0.1700

Data Index: 1229146 (The Pile)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.8868. Min Range: -2.8868

Max Act: 2.8392. Min Act: -0.1700

Data Index: 9097707 (The Pile)

Max Activating Token Index: 376

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.8868. Min Range: -2.8868

Max Act: 2.8392. Min Act: -0.1700

Data Index: 4782552 (The Pile)

Max Activating Token Index: 241

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.8868. Min Range: -2.8868

Max Act: 2.8233. Min Act: -0.1700

Data Index: 689627 (The Pile)

Max Activating Token Index: 175

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.8868. Min Range: -2.8868

Max Act: 2.8073. Min Act: -0.1700

Data Index: 3810365 (The Pile)

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.8868. Min Range: -2.8868

Max Act: 2.7914. Min Act: -0.1700

Data Index: 1527576 (The Pile)

Max Activating Token Index: 613

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.8868. Min Range: -2.8868

Max Act: 2.7914. Min Act: -0.1700

Data Index: 3993901 (The Pile)

Max Activating Token Index: 222

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.8868. Min Range: -2.8868

Max Act: 2.7914. Min Act: -0.1700

Data Index: 6401935 (The Pile)

Max Activating Token Index: 392

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.8868. Min Range: -2.8868

Max Act: 2.7914. Min Act: -0.1700

Data Index: 8001915 (The Pile)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.8868. Min Range: -2.8868

Max Act: 2.7914. Min Act: -0.1700

Data Index: 741197 (The Pile)

Max Activating Token Index: 871

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.8868. Min Range: -2.8868

Max Act: 2.7914. Min Act: -0.1700

Data Index: 7193648 (The Pile)

Max Activating Token Index: 843

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.8868. Min Range: -2.8868

Max Act: 2.7755. Min Act: -0.1700

Data Index: 7732387 (The Pile)

Max Activating Token Index: 651

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.8868. Min Range: -2.8868

Max Act: 2.7755. Min Act: -0.1700

Data Index: 9063839 (The Pile)

Max Activating Token Index: 742

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.8868. Min Range: -2.8868

Max Act: 2.7755. Min Act: -0.1700

Data Index: 829330 (The Pile)

Max Activating Token Index: 496

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.8868. Min Range: -2.8868

Max Act: 2.7595. Min Act: -0.1700

Data Index: 5769941 (The Pile)

Max Activating Token Index: 754

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.8868. Min Range: -2.8868

Max Act: 2.7595. Min Act: -0.1700

Data Index: 8532045 (The Pile)

Max Activating Token Index: 94

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.8868. Min Range: -2.8868

Max Act: 2.7595. Min Act: -0.1700

Data Index: 2352839 (The Pile)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.8868. Min Range: -2.8868

Max Act: 2.7595. Min Act: -0.1700

Data Index: 5495636 (The Pile)

Max Activating Token Index: 666

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.8868. Min Range: -2.8868

Max Act: 2.7595. Min Act: -0.1700

Data Index: 1579234 (The Pile)

Max Activating Token Index: 967

Click toggle to see full text

Truncated

Full Text #19