< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 14 in Layer 21

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.8729. Min Range: -3.8729

Max Act: 3.8729. Min Act: -0.1700

Data Index: 6072036 (The Pile)

Max Activating Token Index: 919

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.8729. Min Range: -3.8729

Max Act: 3.8572. Min Act: -0.1700

Data Index: 3015281 (The Pile)

Max Activating Token Index: 904

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.8729. Min Range: -3.8729

Max Act: 3.8572. Min Act: -0.1700

Data Index: 7138005 (The Pile)

Max Activating Token Index: 103

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.8729. Min Range: -3.8729

Max Act: 3.8259. Min Act: -0.1700

Data Index: 3231604 (The Pile)

Max Activating Token Index: 472

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.8729. Min Range: -3.8729

Max Act: 3.8103. Min Act: -0.1700

Data Index: 6934260 (The Pile)

Max Activating Token Index: 341

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.8729. Min Range: -3.8729

Max Act: 3.7790. Min Act: -0.1700

Data Index: 1928516 (The Pile)

Max Activating Token Index: 82

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.8729. Min Range: -3.8729

Max Act: 3.7321. Min Act: -0.1700

Data Index: 4409374 (The Pile)

Max Activating Token Index: 973

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.8729. Min Range: -3.8729

Max Act: 3.7164. Min Act: -0.1700

Data Index: 9931414 (The Pile)

Max Activating Token Index: 983

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.8729. Min Range: -3.8729

Max Act: 3.7164. Min Act: -0.1700

Data Index: 6220203 (The Pile)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.8729. Min Range: -3.8729

Max Act: 3.7164. Min Act: -0.1700

Data Index: 8495902 (The Pile)

Max Activating Token Index: 364

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.8729. Min Range: -3.8729

Max Act: 3.7008. Min Act: -0.1700

Data Index: 3467482 (The Pile)

Max Activating Token Index: 573

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.8729. Min Range: -3.8729

Max Act: 3.7008. Min Act: -0.1700

Data Index: 7574244 (The Pile)

Max Activating Token Index: 383

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.8729. Min Range: -3.8729

Max Act: 3.7008. Min Act: -0.1700

Data Index: 3578676 (The Pile)

Max Activating Token Index: 896

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.8729. Min Range: -3.8729

Max Act: 3.6851. Min Act: -0.1700

Data Index: 10412796 (The Pile)

Max Activating Token Index: 57

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.8729. Min Range: -3.8729

Max Act: 3.6851. Min Act: -0.1700

Data Index: 8739980 (The Pile)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.8729. Min Range: -3.8729

Max Act: 3.6851. Min Act: -0.1700

Data Index: 5590722 (The Pile)

Max Activating Token Index: 383

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.8729. Min Range: -3.8729

Max Act: 3.6851. Min Act: -0.1700

Data Index: 7166209 (The Pile)

Max Activating Token Index: 173

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.8729. Min Range: -3.8729

Max Act: 3.6695. Min Act: -0.1700

Data Index: 3240681 (The Pile)

Max Activating Token Index: 814

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.8729. Min Range: -3.8729

Max Act: 3.6695. Min Act: -0.1700

Data Index: 7646336 (The Pile)

Max Activating Token Index: 732

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.8729. Min Range: -3.8729

Max Act: 3.6695. Min Act: -0.1700

Data Index: 2901518 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #19