< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 8 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: 2.0771. Min Range: -2.0771

Max Act: 2.0771. Min Act: -0.1700

Data Index: 2537721 (The Pile)

Max Activating Token Index: 447

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.0771. Min Range: -2.0771

Max Act: 2.0098. Min Act: -0.1700

Data Index: 5676531 (The Pile)

Max Activating Token Index: 767

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.0771. Min Range: -2.0771

Max Act: 2.0098. Min Act: -0.1700

Data Index: 3074276 (The Pile)

Max Activating Token Index: 699

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.9760. Min Act: -0.1700

Data Index: 7860897 (The Pile)

Max Activating Token Index: 143

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.9760. Min Act: -0.1700

Data Index: 1278723 (The Pile)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.9591. Min Act: -0.1700

Data Index: 5055910 (The Pile)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.9591. Min Act: -0.1700

Data Index: 7655418 (The Pile)

Max Activating Token Index: 605

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.9251. Min Act: -0.1700

Data Index: 7449872 (The Pile)

Max Activating Token Index: 653

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.9421. Min Act: -0.1700

Data Index: 3011685 (The Pile)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.9421. Min Act: -0.1700

Data Index: 2558565 (The Pile)

Max Activating Token Index: 868

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.9251. Min Act: -0.1700

Data Index: 9374370 (The Pile)

Max Activating Token Index: 343

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.9421. Min Act: -0.1700

Data Index: 1920480 (The Pile)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.9081. Min Act: -0.1700

Data Index: 2005023 (The Pile)

Max Activating Token Index: 635

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.9081. Min Act: -0.1700

Data Index: 1033663 (The Pile)

Max Activating Token Index: 314

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.9251. Min Act: -0.1700

Data Index: 1037452 (The Pile)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.9251. Min Act: -0.1699

Data Index: 3403756 (The Pile)

Max Activating Token Index: 697

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.9081. Min Act: -0.1700

Data Index: 3904240 (The Pile)

Max Activating Token Index: 714

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.8911. Min Act: -0.1700

Data Index: 8787868 (The Pile)

Max Activating Token Index: 513

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.9421. Min Act: -0.1700

Data Index: 6207005 (The Pile)

Max Activating Token Index: 433

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.9081. Min Act: -0.1700

Data Index: 1293307 (The Pile)

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #19