< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 10 in Layer 13

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.1619. Min Range: -3.1619

Max Act: 3.1619. Min Act: -0.1700

Data Index: 7558133 (The Pile)

Max Activating Token Index: 354

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.1619. Min Range: -3.1619

Max Act: 3.0989. Min Act: -0.1700

Data Index: 2176175 (The Pile)

Max Activating Token Index: 315

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.1619. Min Range: -3.1619

Max Act: 3.0515. Min Act: -0.1700

Data Index: 2493270 (The Pile)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.1619. Min Range: -3.1619

Max Act: 3.0357. Min Act: -0.1700

Data Index: 1737568 (The Pile)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.1619. Min Range: -3.1619

Max Act: 3.0357. Min Act: -0.1700

Data Index: 1800915 (The Pile)

Max Activating Token Index: 814

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.1619. Min Range: -3.1619

Max Act: 3.0199. Min Act: -0.1700

Data Index: 3492296 (The Pile)

Max Activating Token Index: 470

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.1619. Min Range: -3.1619

Max Act: 3.0041. Min Act: -0.1700

Data Index: 3231940 (The Pile)

Max Activating Token Index: 144

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.1619. Min Range: -3.1619

Max Act: 3.0041. Min Act: -0.1700

Data Index: 2773715 (The Pile)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.1619. Min Range: -3.1619

Max Act: 3.0041. Min Act: -0.1700

Data Index: 5440835 (The Pile)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.1619. Min Range: -3.1619

Max Act: 3.0041. Min Act: -0.1700

Data Index: 8486649 (The Pile)

Max Activating Token Index: 943

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.1619. Min Range: -3.1619

Max Act: 3.0041. Min Act: -0.1700

Data Index: 9179636 (The Pile)

Max Activating Token Index: 418

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.1619. Min Range: -3.1619

Max Act: 2.9883. Min Act: -0.1700

Data Index: 5163072 (The Pile)

Max Activating Token Index: 724

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.1619. Min Range: -3.1619

Max Act: 2.9725. Min Act: -0.1700

Data Index: 5015658 (The Pile)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.1619. Min Range: -3.1619

Max Act: 2.9725. Min Act: -0.1700

Data Index: 4358833 (The Pile)

Max Activating Token Index: 1012

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.1619. Min Range: -3.1619

Max Act: 2.9725. Min Act: -0.1700

Data Index: 4331192 (The Pile)

Max Activating Token Index: 996

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.1619. Min Range: -3.1619

Max Act: 2.9725. Min Act: -0.1700

Data Index: 2177639 (The Pile)

Max Activating Token Index: 723

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.1619. Min Range: -3.1619

Max Act: 2.9725. Min Act: -0.1700

Data Index: 9494024 (The Pile)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.1619. Min Range: -3.1619

Max Act: 2.9567. Min Act: -0.1700

Data Index: 5541534 (The Pile)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.1619. Min Range: -3.1619

Max Act: 2.9567. Min Act: -0.1700

Data Index: 1359036 (The Pile)

Max Activating Token Index: 678

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.1619. Min Range: -3.1619

Max Act: 2.9567. Min Act: -0.1700

Data Index: 9239795 (The Pile)

Max Activating Token Index: 727

Click toggle to see full text

Truncated

Full Text #19