< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2010 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.8074. Min Range: -3.8074

Max Act: 3.8074. Min Act: -0.1700

Data Index: 6601115 (The Pile)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.8074. Min Range: -3.8074

Max Act: 3.8074. Min Act: -0.1700

Data Index: 1469058 (The Pile)

Max Activating Token Index: 600

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.8074. Min Range: -3.8074

Max Act: 3.8074. Min Act: -0.1700

Data Index: 5564108 (The Pile)

Max Activating Token Index: 816

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.8074. Min Range: -3.8074

Max Act: 3.8074. Min Act: -0.1700

Data Index: 6167711 (The Pile)

Max Activating Token Index: 842

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.8074. Min Range: -3.8074

Max Act: 3.7449. Min Act: -0.1700

Data Index: 1958650 (The Pile)

Max Activating Token Index: 714

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.8074. Min Range: -3.8074

Max Act: 3.7449. Min Act: -0.1700

Data Index: 6601923 (The Pile)

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.8074. Min Range: -3.8074

Max Act: 3.7449. Min Act: -0.1700

Data Index: 3576861 (The Pile)

Max Activating Token Index: 875

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.8074. Min Range: -3.8074

Max Act: 3.7292. Min Act: -0.1700

Data Index: 8784393 (The Pile)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.8074. Min Range: -3.8074

Max Act: 3.7292. Min Act: -0.1700

Data Index: 6776436 (The Pile)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.8074. Min Range: -3.8074

Max Act: 3.7292. Min Act: -0.1700

Data Index: 8629393 (The Pile)

Max Activating Token Index: 788

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.8074. Min Range: -3.8074

Max Act: 3.7292. Min Act: -0.1700

Data Index: 5887558 (The Pile)

Max Activating Token Index: 846

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.8074. Min Range: -3.8074

Max Act: 3.7292. Min Act: -0.1700

Data Index: 3768278 (The Pile)

Max Activating Token Index: 756

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.8074. Min Range: -3.8074

Max Act: 3.7292. Min Act: -0.1700

Data Index: 5593348 (The Pile)

Max Activating Token Index: 663

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.8074. Min Range: -3.8074

Max Act: 3.7136. Min Act: -0.1700

Data Index: 798320 (The Pile)

Max Activating Token Index: 698

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.8074. Min Range: -3.8074

Max Act: 3.7136. Min Act: -0.1700

Data Index: 6575482 (The Pile)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.8074. Min Range: -3.8074

Max Act: 3.7136. Min Act: -0.1700

Data Index: 2026597 (The Pile)

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.8074. Min Range: -3.8074

Max Act: 3.6979. Min Act: -0.1700

Data Index: 473336 (The Pile)

Max Activating Token Index: 896

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.8074. Min Range: -3.8074

Max Act: 3.6979. Min Act: -0.1700

Data Index: 5425011 (The Pile)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.8074. Min Range: -3.8074

Max Act: 3.6979. Min Act: -0.1700

Data Index: 7447591 (The Pile)

Max Activating Token Index: 879

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.8074. Min Range: -3.8074

Max Act: 3.6979. Min Act: -0.1700

Data Index: 2252144 (The Pile)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #19