< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 16 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.6616. Min Range: -4.6616

Max Act: 4.6616. Min Act: -0.1700

Data Index: 9275767 (The Pile)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.6616. Min Range: -4.6616

Max Act: 4.5991. Min Act: -0.1700

Data Index: 6195414 (The Pile)

Max Activating Token Index: 594

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.6616. Min Range: -4.6616

Max Act: 4.4116. Min Act: -0.1700

Data Index: 6002999 (The Pile)

Max Activating Token Index: 540

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.6616. Min Range: -4.6616

Max Act: 4.3803. Min Act: -0.1700

Data Index: 3965269 (The Pile)

Max Activating Token Index: 1012

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.6616. Min Range: -4.6616

Max Act: 4.3491. Min Act: -0.1700

Data Index: 9872287 (The Pile)

Max Activating Token Index: 208

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.6616. Min Range: -4.6616

Max Act: 4.2553. Min Act: -0.1700

Data Index: 5322132 (The Pile)

Max Activating Token Index: 748

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.6616. Min Range: -4.6616

Max Act: 4.4116. Min Act: -0.1700

Data Index: 5131434 (The Pile)

Max Activating Token Index: 886

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.6616. Min Range: -4.6616

Max Act: 4.1615. Min Act: -0.1700

Data Index: 3719176 (The Pile)

Max Activating Token Index: 1009

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.6616. Min Range: -4.6616

Max Act: 4.3803. Min Act: -0.1700

Data Index: 860958 (The Pile)

Max Activating Token Index: 577

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.6616. Min Range: -4.6616

Max Act: 4.3491. Min Act: -0.1700

Data Index: 5248824 (The Pile)

Max Activating Token Index: 537

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.6616. Min Range: -4.6616

Max Act: 4.3803. Min Act: -0.1700

Data Index: 1456387 (The Pile)

Max Activating Token Index: 880

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.6616. Min Range: -4.6616

Max Act: 4.2553. Min Act: -0.1700

Data Index: 4084148 (The Pile)

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.6616. Min Range: -4.6616

Max Act: 4.3178. Min Act: -0.1700

Data Index: 9730346 (The Pile)

Max Activating Token Index: 775

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.6616. Min Range: -4.6616

Max Act: 4.5053. Min Act: -0.1700

Data Index: 7855854 (The Pile)

Max Activating Token Index: 723

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.6616. Min Range: -4.6616

Max Act: 4.2241. Min Act: -0.1700

Data Index: 1619264 (The Pile)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.6616. Min Range: -4.6616

Max Act: 4.5678. Min Act: -0.1700

Data Index: 9761451 (The Pile)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.6616. Min Range: -4.6616

Max Act: 4.2241. Min Act: -0.1700

Data Index: 2466638 (The Pile)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.6616. Min Range: -4.6616

Max Act: 4.3803. Min Act: -0.1700

Data Index: 4018271 (The Pile)

Max Activating Token Index: 375

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.6616. Min Range: -4.6616

Max Act: 4.2241. Min Act: -0.1700

Data Index: 8373789 (The Pile)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.6616. Min Range: -4.6616

Max Act: 4.2553. Min Act: -0.1700

Data Index: 4913346 (The Pile)

Max Activating Token Index: 991

Click toggle to see full text

Truncated

Full Text #19