< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2028 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 2.7344. Min Range: -2.7344

Max Act: 2.7344. Min Act: -0.1700

Data Index: 8720757 (The Pile)

Max Activating Token Index: 881

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.7344. Min Range: -2.7344

Max Act: 2.7185. Min Act: -0.1700

Data Index: 6525124 (The Pile)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.7344. Min Range: -2.7344

Max Act: 2.7344. Min Act: -0.1700

Data Index: 3702351 (The Pile)

Max Activating Token Index: 1014

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.7344. Min Range: -2.7344

Max Act: 2.7185. Min Act: -0.1700

Data Index: 7160674 (The Pile)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.7344. Min Range: -2.7344

Max Act: 2.6865. Min Act: -0.1700

Data Index: 9822193 (The Pile)

Max Activating Token Index: 837

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.7344. Min Range: -2.7344

Max Act: 2.7185. Min Act: -0.1700

Data Index: 8981984 (The Pile)

Max Activating Token Index: 657

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.7344. Min Range: -2.7344

Max Act: 2.6865. Min Act: -0.1700

Data Index: 9725433 (The Pile)

Max Activating Token Index: 937

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.7344. Min Range: -2.7344

Max Act: 2.6704. Min Act: -0.1700

Data Index: 4474144 (The Pile)

Max Activating Token Index: 390

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.7344. Min Range: -2.7344

Max Act: 2.7025. Min Act: -0.1700

Data Index: 8219628 (The Pile)

Max Activating Token Index: 920

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.7344. Min Range: -2.7344

Max Act: 2.6865. Min Act: -0.1700

Data Index: 2596766 (The Pile)

Max Activating Token Index: 282

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.7344. Min Range: -2.7344

Max Act: 2.6865. Min Act: -0.1700

Data Index: 4685574 (The Pile)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.7344. Min Range: -2.7344

Max Act: 2.6865. Min Act: -0.1700

Data Index: 2899150 (The Pile)

Max Activating Token Index: 694

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.7344. Min Range: -2.7344

Max Act: 2.6544. Min Act: -0.1700

Data Index: 8035342 (The Pile)

Max Activating Token Index: 424

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.7344. Min Range: -2.7344

Max Act: 2.6544. Min Act: -0.1700

Data Index: 8457907 (The Pile)

Max Activating Token Index: 775

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.7344. Min Range: -2.7344

Max Act: 2.6704. Min Act: -0.1700

Data Index: 8677470 (The Pile)

Max Activating Token Index: 99

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.7344. Min Range: -2.7344

Max Act: 2.6223. Min Act: -0.1700

Data Index: 5757506 (The Pile)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.7344. Min Range: -2.7344

Max Act: 2.6704. Min Act: -0.1700

Data Index: 4550763 (The Pile)

Max Activating Token Index: 252

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.7344. Min Range: -2.7344

Max Act: 2.6704. Min Act: -0.1700

Data Index: 8682058 (The Pile)

Max Activating Token Index: 620

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.7344. Min Range: -2.7344

Max Act: 2.6544. Min Act: -0.1700

Data Index: 2305443 (The Pile)

Max Activating Token Index: 664

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.7344. Min Range: -2.7344

Max Act: 2.6704. Min Act: -0.1700

Data Index: 6390761 (The Pile)

Max Activating Token Index: 527

Click toggle to see full text

Truncated

Full Text #19