< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 28 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: 3.3568. Min Range: -3.3568

Max Act: 3.3568. Min Act: -0.1700

Data Index: 8418476 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.3097. Min Act: -0.1700

Data Index: 8104845 (The Pile)

Max Activating Token Index: 16

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.2154. Min Act: -0.1700

Data Index: 2567110 (The Pile)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1997. Min Act: -0.1700

Data Index: 10701936 (The Pile)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1997. Min Act: -0.1700

Data Index: 3432668 (The Pile)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1997. Min Act: -0.1700

Data Index: 1134280 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1997. Min Act: -0.1700

Data Index: 1888570 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1840. Min Act: -0.1700

Data Index: 3555291 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1840. Min Act: -0.1700

Data Index: 1211903 (The Pile)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1840. Min Act: -0.1700

Data Index: 7746560 (The Pile)

Max Activating Token Index: 52

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1682. Min Act: -0.1700

Data Index: 302681 (The Pile)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1682. Min Act: -0.1700

Data Index: 3629926 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1682. Min Act: -0.1700

Data Index: 7408254 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1840. Min Act: -0.1700

Data Index: 1193040 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1682. Min Act: -0.1700

Data Index: 7499622 (The Pile)

Max Activating Token Index: 44

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1682. Min Act: -0.1700

Data Index: 8080221 (The Pile)

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1525. Min Act: -0.1700

Data Index: 8144359 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1525. Min Act: -0.1700

Data Index: 4159315 (The Pile)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1525. Min Act: -0.1700

Data Index: 3825193 (The Pile)

Max Activating Token Index: 23

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1525. Min Act: -0.1700

Data Index: 1742840 (The Pile)

Max Activating Token Index: 74

Click toggle to see full text

Truncated

Full Text #19