< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4028 in Layer 15

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.1681. Min Range: -4.1681

Max Act: 4.1681. Min Act: -0.1700

Data Index: 1680450 (The Pile)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.1681. Min Range: -4.1681

Max Act: 4.0743. Min Act: -0.1700

Data Index: 7459566 (The Pile)

Max Activating Token Index: 997

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.1681. Min Range: -4.1681

Max Act: 4.0743. Min Act: -0.1700

Data Index: 696427 (The Pile)

Max Activating Token Index: 591

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.1681. Min Range: -4.1681

Max Act: 4.0743. Min Act: -0.1700

Data Index: 6206988 (The Pile)

Max Activating Token Index: 843

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.1681. Min Range: -4.1681

Max Act: 4.0430. Min Act: -0.1700

Data Index: 577922 (The Pile)

Max Activating Token Index: 647

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.1681. Min Range: -4.1681

Max Act: 4.0430. Min Act: -0.1700

Data Index: 6818717 (The Pile)

Max Activating Token Index: 341

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.1681. Min Range: -4.1681

Max Act: 4.0430. Min Act: -0.1700

Data Index: 6235998 (The Pile)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.1681. Min Range: -4.1681

Max Act: 4.0430. Min Act: -0.1700

Data Index: 3258302 (The Pile)

Max Activating Token Index: 367

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.1681. Min Range: -4.1681

Max Act: 4.0118. Min Act: -0.1700

Data Index: 7407060 (The Pile)

Max Activating Token Index: 441

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.1681. Min Range: -4.1681

Max Act: 3.9805. Min Act: -0.1700

Data Index: 3573305 (The Pile)

Max Activating Token Index: 491

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.1681. Min Range: -4.1681

Max Act: 3.9805. Min Act: -0.1700

Data Index: 7615972 (The Pile)

Max Activating Token Index: 589

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.1681. Min Range: -4.1681

Max Act: 3.9805. Min Act: -0.1700

Data Index: 1420374 (The Pile)

Max Activating Token Index: 543

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.1681. Min Range: -4.1681

Max Act: 3.9805. Min Act: -0.1700

Data Index: 6115279 (The Pile)

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.1681. Min Range: -4.1681

Max Act: 3.9805. Min Act: -0.1700

Data Index: 10448595 (The Pile)

Max Activating Token Index: 722

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.1681. Min Range: -4.1681

Max Act: 3.9649. Min Act: -0.1700

Data Index: 9848163 (The Pile)

Max Activating Token Index: 857

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.1681. Min Range: -4.1681

Max Act: 3.9649. Min Act: -0.1700

Data Index: 9116090 (The Pile)

Max Activating Token Index: 922

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.1681. Min Range: -4.1681

Max Act: 3.9649. Min Act: -0.1700

Data Index: 4962757 (The Pile)

Max Activating Token Index: 558

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.1681. Min Range: -4.1681

Max Act: 3.9649. Min Act: -0.1700

Data Index: 8724655 (The Pile)

Max Activating Token Index: 831

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.1681. Min Range: -4.1681

Max Act: 3.9492. Min Act: -0.1700

Data Index: 7034825 (The Pile)

Max Activating Token Index: 668

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.1681. Min Range: -4.1681

Max Act: 3.9336. Min Act: -0.1700

Data Index: 1071718 (The Pile)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #19