< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 28 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.5195. Min Act: -0.1698

Data Index: 9278382 (The Pile)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.5352. Min Act: -0.1700

Data Index: 7014792 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.5508. Min Act: -0.1700

Data Index: 8512665 (The Pile)

Max Activating Token Index: 458

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.3627. Min Act: -0.1700

Data Index: 1570188 (The Pile)

Max Activating Token Index: 721

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.3941. Min Act: -0.1699

Data Index: 10396124 (The Pile)

Max Activating Token Index: 676

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.4411. Min Act: -0.1700

Data Index: 7865130 (The Pile)

Max Activating Token Index: 559

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.5038. Min Act: -0.1699

Data Index: 58666 (The Pile)

Max Activating Token Index: 553

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.3627. Min Act: -0.1700

Data Index: 1418823 (The Pile)

Max Activating Token Index: 216

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.4882. Min Act: -0.1700

Data Index: 536308 (The Pile)

Max Activating Token Index: 990

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.3941. Min Act: -0.1700

Data Index: 8580042 (The Pile)

Max Activating Token Index: 998

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.3627. Min Act: -0.1700

Data Index: 1910997 (The Pile)

Max Activating Token Index: 508

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.4255. Min Act: -0.1700

Data Index: 3001615 (The Pile)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.5195. Min Act: -0.1700

Data Index: 6006401 (The Pile)

Max Activating Token Index: 699

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.2371. Min Act: -0.1696

Data Index: 6420470 (The Pile)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.2999. Min Act: -0.1700

Data Index: 6384484 (The Pile)

Max Activating Token Index: 390

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.3941. Min Act: -0.1700

Data Index: 10570237 (The Pile)

Max Activating Token Index: 157

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.4568. Min Act: -0.1697

Data Index: 3760634 (The Pile)

Max Activating Token Index: 309

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.3627. Min Act: -0.1699

Data Index: 3670971 (The Pile)

Max Activating Token Index: 722

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.4725. Min Act: -0.1699

Data Index: 4377474 (The Pile)

Max Activating Token Index: 528

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.5508. Min Range: -3.5508

Max Act: 3.3627. Min Act: -0.1699

Data Index: 5218898 (The Pile)

Max Activating Token Index: 174

Click toggle to see full text

Truncated

Full Text #19