< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1117 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: 4.7194. Min Range: -4.7194

Max Act: 4.7194. Min Act: -0.1700

Data Index: 1055837 (The Pile)

Max Activating Token Index: 26

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5943. Min Act: -0.1700

Data Index: 10078256 (The Pile)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5943. Min Act: -0.1700

Data Index: 4142764 (The Pile)

Max Activating Token Index: 228

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.6256. Min Act: -0.1699

Data Index: 4179713 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5943. Min Act: -0.1700

Data Index: 9967686 (The Pile)

Max Activating Token Index: 23

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5943. Min Act: -0.1700

Data Index: 8738359 (The Pile)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.6256. Min Act: -0.1697

Data Index: 6820123 (The Pile)

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5943. Min Act: -0.1700

Data Index: 4150773 (The Pile)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5318. Min Act: -0.1700

Data Index: 324606 (The Pile)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.4693. Min Act: -0.1699

Data Index: 9724933 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5006. Min Act: -0.1699

Data Index: 1439566 (The Pile)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.4381. Min Act: -0.1700

Data Index: 3848626 (The Pile)

Max Activating Token Index: 914

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.4693. Min Act: -0.1700

Data Index: 7606575 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.4693. Min Act: -0.1699

Data Index: 4758541 (The Pile)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.5006. Min Act: -0.1700

Data Index: 4457362 (The Pile)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.4693. Min Act: -0.1700

Data Index: 2618286 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.4693. Min Act: -0.1700

Data Index: 368033 (The Pile)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.4381. Min Act: -0.1700

Data Index: 1907435 (The Pile)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.4693. Min Act: -0.1700

Data Index: 4284805 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.7194. Min Range: -4.7194

Max Act: 4.4381. Min Act: -0.1698

Data Index: 330474 (The Pile)

Max Activating Token Index: 54

Click toggle to see full text

Truncated

Full Text #19