< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4052 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.8835. Min Act: -0.1700

Data Index: 10118278 (The Pile)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.8678. Min Act: -0.1700

Data Index: 2076542 (The Pile)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.8209. Min Act: -0.1700

Data Index: 3332415 (The Pile)

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.8053. Min Act: -0.1700

Data Index: 7592514 (The Pile)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.7896. Min Act: -0.1700

Data Index: 6045266 (The Pile)

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.7427. Min Act: -0.1700

Data Index: 3456459 (The Pile)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.7427. Min Act: -0.1700

Data Index: 4013619 (The Pile)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.7427. Min Act: -0.1700

Data Index: 5764536 (The Pile)

Max Activating Token Index: 102

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.7271. Min Act: -0.1700

Data Index: 8466439 (The Pile)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.7271. Min Act: -0.1700

Data Index: 9812435 (The Pile)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.7271. Min Act: -0.1700

Data Index: 6795793 (The Pile)

Max Activating Token Index: 247

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.7114. Min Act: -0.1700

Data Index: 5975743 (The Pile)

Max Activating Token Index: 137

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.7114. Min Act: -0.1700

Data Index: 9022603 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.7114. Min Act: -0.1700

Data Index: 8551807 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.6958. Min Act: -0.1700

Data Index: 4147232 (The Pile)

Max Activating Token Index: 109

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.6958. Min Act: -0.1700

Data Index: 8610153 (The Pile)

Max Activating Token Index: 975

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.6801. Min Act: -0.1700

Data Index: 6709090 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.6801. Min Act: -0.1700

Data Index: 686934 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.6645. Min Act: -0.1700

Data Index: 113922 (The Pile)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.6645. Min Act: -0.1700

Data Index: 5471582 (The Pile)

Max Activating Token Index: 339

Click toggle to see full text

Truncated

Full Text #19