< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4063 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.7224. Min Act: -0.1700

Data Index: 3791837 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.5971. Min Act: -0.1700

Data Index: 9862535 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.5815. Min Act: -0.1700

Data Index: 9539565 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.5032. Min Act: -0.1700

Data Index: 10681485 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.4875. Min Act: -0.1700

Data Index: 10788538 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.4875. Min Act: -0.1700

Data Index: 6874724 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.4875. Min Act: -0.1700

Data Index: 2793875 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.4718. Min Act: -0.1700

Data Index: 5931994 (The Pile)

Max Activating Token Index: 814

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.4561. Min Act: -0.1700

Data Index: 564480 (The Pile)

Max Activating Token Index: 978

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.4561. Min Act: -0.1700

Data Index: 7966177 (The Pile)

Max Activating Token Index: 714

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.4405. Min Act: -0.1700

Data Index: 10484924 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.4405. Min Act: -0.1700

Data Index: 10265541 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.4405. Min Act: -0.1700

Data Index: 6599480 (The Pile)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.4248. Min Act: -0.1700

Data Index: 8107248 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.4248. Min Act: -0.1700

Data Index: 8487347 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.4248. Min Act: -0.1700

Data Index: 6578203 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.4248. Min Act: -0.1700

Data Index: 4565684 (The Pile)

Max Activating Token Index: 403

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.4091. Min Act: -0.1700

Data Index: 511382 (The Pile)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.4091. Min Act: -0.1700

Data Index: 6298796 (The Pile)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.7224. Min Range: -3.7224

Max Act: 3.4091. Min Act: -0.1700

Data Index: 3608914 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #19