< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 55 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: 3.0817. Min Range: -3.0817

Max Act: 3.0817. Min Act: -0.1700

Data Index: 618370 (The Pile)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.0817. Min Range: -3.0817

Max Act: 3.0501. Min Act: -0.1700

Data Index: 7034254 (The Pile)

Max Activating Token Index: 677

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.0817. Min Range: -3.0817

Max Act: 3.0501. Min Act: -0.1700

Data Index: 1873309 (The Pile)

Max Activating Token Index: 144

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.0817. Min Range: -3.0817

Max Act: 3.0343. Min Act: -0.1700

Data Index: 4190602 (The Pile)

Max Activating Token Index: 507

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.0817. Min Range: -3.0817

Max Act: 3.0185. Min Act: -0.1700

Data Index: 5861152 (The Pile)

Max Activating Token Index: 585

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.0817. Min Range: -3.0817

Max Act: 3.0027. Min Act: -0.1700

Data Index: 9248010 (The Pile)

Max Activating Token Index: 560

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.0817. Min Range: -3.0817

Max Act: 2.9711. Min Act: -0.1700

Data Index: 7040023 (The Pile)

Max Activating Token Index: 934

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.0817. Min Range: -3.0817

Max Act: 2.9869. Min Act: -0.1700

Data Index: 2148881 (The Pile)

Max Activating Token Index: 766

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.0817. Min Range: -3.0817

Max Act: 3.0027. Min Act: -0.1700

Data Index: 9285271 (The Pile)

Max Activating Token Index: 383

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.0817. Min Range: -3.0817

Max Act: 2.9869. Min Act: -0.1700

Data Index: 6063605 (The Pile)

Max Activating Token Index: 703

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.0817. Min Range: -3.0817

Max Act: 2.9394. Min Act: -0.1700

Data Index: 862477 (The Pile)

Max Activating Token Index: 868

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.0817. Min Range: -3.0817

Max Act: 2.9711. Min Act: -0.1700

Data Index: 5403504 (The Pile)

Max Activating Token Index: 507

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.0817. Min Range: -3.0817

Max Act: 2.9869. Min Act: -0.1700

Data Index: 4855206 (The Pile)

Max Activating Token Index: 619

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.0817. Min Range: -3.0817

Max Act: 2.9394. Min Act: -0.1700

Data Index: 3470849 (The Pile)

Max Activating Token Index: 375

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.0817. Min Range: -3.0817

Max Act: 2.9869. Min Act: -0.1700

Data Index: 3098514 (The Pile)

Max Activating Token Index: 1009

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.0817. Min Range: -3.0817

Max Act: 2.9711. Min Act: -0.1700

Data Index: 7777858 (The Pile)

Max Activating Token Index: 636

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.0817. Min Range: -3.0817

Max Act: 2.9553. Min Act: -0.1700

Data Index: 4339020 (The Pile)

Max Activating Token Index: 87

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.0817. Min Range: -3.0817

Max Act: 2.9077. Min Act: -0.1700

Data Index: 6284833 (The Pile)

Max Activating Token Index: 916

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.0817. Min Range: -3.0817

Max Act: 2.9553. Min Act: -0.1700

Data Index: 6106162 (The Pile)

Max Activating Token Index: 861

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.0817. Min Range: -3.0817

Max Act: 2.9236. Min Act: -0.1700

Data Index: 5487013 (The Pile)

Max Activating Token Index: 802

Click toggle to see full text

Truncated

Full Text #19