< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 3028 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 2.6598. Min Range: -2.6598

Max Act: 2.6598. Min Act: -0.1700

Data Index: 126408 (The Pile)

Max Activating Token Index: 427

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.6598. Min Range: -2.6598

Max Act: 2.6438. Min Act: -0.1700

Data Index: 3140088 (The Pile)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.6598. Min Range: -2.6598

Max Act: 2.6438. Min Act: -0.1700

Data Index: 7176866 (The Pile)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.6598. Min Range: -2.6598

Max Act: 2.6438. Min Act: -0.1700

Data Index: 2066185 (The Pile)

Max Activating Token Index: 657

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.6598. Min Range: -2.6598

Max Act: 2.6277. Min Act: -0.1700

Data Index: 8406109 (The Pile)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.6598. Min Range: -2.6598

Max Act: 2.6277. Min Act: -0.1700

Data Index: 4919718 (The Pile)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.6598. Min Range: -2.6598

Max Act: 2.6116. Min Act: -0.1700

Data Index: 1341742 (The Pile)

Max Activating Token Index: 952

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.6598. Min Range: -2.6598

Max Act: 2.5956. Min Act: -0.1700

Data Index: 6936183 (The Pile)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.6598. Min Range: -2.6598

Max Act: 2.5956. Min Act: -0.1700

Data Index: 3132012 (The Pile)

Max Activating Token Index: 1015

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.6598. Min Range: -2.6598

Max Act: 2.5956. Min Act: -0.1700

Data Index: 5247734 (The Pile)

Max Activating Token Index: 459

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.6598. Min Range: -2.6598

Max Act: 2.5956. Min Act: -0.1700

Data Index: 3632714 (The Pile)

Max Activating Token Index: 593

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.6598. Min Range: -2.6598

Max Act: 2.5956. Min Act: -0.1700

Data Index: 7579672 (The Pile)

Max Activating Token Index: 794

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.6598. Min Range: -2.6598

Max Act: 2.5795. Min Act: -0.1700

Data Index: 1853472 (The Pile)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.6598. Min Range: -2.6598

Max Act: 2.5795. Min Act: -0.1700

Data Index: 4748021 (The Pile)

Max Activating Token Index: 711

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.6598. Min Range: -2.6598

Max Act: 2.5795. Min Act: -0.1700

Data Index: 7791855 (The Pile)

Max Activating Token Index: 1012

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.6598. Min Range: -2.6598

Max Act: 2.5795. Min Act: -0.1700

Data Index: 9760921 (The Pile)

Max Activating Token Index: 374

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.6598. Min Range: -2.6598

Max Act: 2.5633. Min Act: -0.1700

Data Index: 10429600 (The Pile)

Max Activating Token Index: 446

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.6598. Min Range: -2.6598

Max Act: 2.5633. Min Act: -0.1700

Data Index: 1038488 (The Pile)

Max Activating Token Index: 502

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.6598. Min Range: -2.6598

Max Act: 2.5472. Min Act: -0.1700

Data Index: 8347328 (The Pile)

Max Activating Token Index: 768

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.6598. Min Range: -2.6598

Max Act: 2.5472. Min Act: -0.1700

Data Index: 2760201 (The Pile)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #19