< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4057 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.2605. Min Range: -3.2605

Max Act: 3.2605. Min Act: -0.1700

Data Index: 10118588 (The Pile)

Max Activating Token Index: 891

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2605. Min Range: -3.2605

Max Act: 3.1976. Min Act: -0.1700

Data Index: 2938526 (The Pile)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2605. Min Range: -3.2605

Max Act: 3.1504. Min Act: -0.1700

Data Index: 9167506 (The Pile)

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2605. Min Range: -3.2605

Max Act: 3.1346. Min Act: -0.1700

Data Index: 6452529 (The Pile)

Max Activating Token Index: 950

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2605. Min Range: -3.2605

Max Act: 3.1346. Min Act: -0.1700

Data Index: 7565379 (The Pile)

Max Activating Token Index: 111

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2605. Min Range: -3.2605

Max Act: 3.1346. Min Act: -0.1700

Data Index: 732200 (The Pile)

Max Activating Token Index: 650

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2605. Min Range: -3.2605

Max Act: 3.1346. Min Act: -0.1700

Data Index: 9171615 (The Pile)

Max Activating Token Index: 478

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2605. Min Range: -3.2605

Max Act: 3.1346. Min Act: -0.1700

Data Index: 10000673 (The Pile)

Max Activating Token Index: 107

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2605. Min Range: -3.2605

Max Act: 3.1189. Min Act: -0.1700

Data Index: 7682737 (The Pile)

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2605. Min Range: -3.2605

Max Act: 3.1189. Min Act: -0.1700

Data Index: 7671159 (The Pile)

Max Activating Token Index: 791

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2605. Min Range: -3.2605

Max Act: 3.1189. Min Act: -0.1700

Data Index: 5790082 (The Pile)

Max Activating Token Index: 644

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2605. Min Range: -3.2605

Max Act: 3.1189. Min Act: -0.1700

Data Index: 8218015 (The Pile)

Max Activating Token Index: 266

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2605. Min Range: -3.2605

Max Act: 3.1031. Min Act: -0.1700

Data Index: 4529329 (The Pile)

Max Activating Token Index: 375

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2605. Min Range: -3.2605

Max Act: 3.1031. Min Act: -0.1700

Data Index: 3394800 (The Pile)

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2605. Min Range: -3.2605

Max Act: 3.1031. Min Act: -0.1700

Data Index: 2604702 (The Pile)

Max Activating Token Index: 714

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2605. Min Range: -3.2605

Max Act: 3.1031. Min Act: -0.1700

Data Index: 3742947 (The Pile)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2605. Min Range: -3.2605

Max Act: 3.1031. Min Act: -0.1700

Data Index: 8613395 (The Pile)

Max Activating Token Index: 109

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2605. Min Range: -3.2605

Max Act: 3.1031. Min Act: -0.1700

Data Index: 8069877 (The Pile)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2605. Min Range: -3.2605

Max Act: 3.0873. Min Act: -0.1700

Data Index: 83055 (The Pile)

Max Activating Token Index: 1007

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2605. Min Range: -3.2605

Max Act: 3.0873. Min Act: -0.1700

Data Index: 1781415 (The Pile)

Max Activating Token Index: 751

Click toggle to see full text

Truncated

Full Text #19