< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 21 in Layer 19

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 22.9065. Min Range: -22.9065

Max Act: 22.9065. Min Act: -0.1700

Data Index: 8372648 (The Pile)

Max Activating Token Index: 688

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 22.9065. Min Range: -22.9065

Max Act: 22.9065. Min Act: -0.1700

Data Index: 6029128 (The Pile)

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 22.9065. Min Range: -22.9065

Max Act: 22.7815. Min Act: -0.1700

Data Index: 7911022 (The Pile)

Max Activating Token Index: 188

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 22.9065. Min Range: -22.9065

Max Act: 22.7815. Min Act: -0.1700

Data Index: 670993 (The Pile)

Max Activating Token Index: 325

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 22.9065. Min Range: -22.9065

Max Act: 22.7815. Min Act: -0.1700

Data Index: 7911932 (The Pile)

Max Activating Token Index: 741

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 22.9065. Min Range: -22.9065

Max Act: 22.6565. Min Act: -0.1700

Data Index: 7509762 (The Pile)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 22.9065. Min Range: -22.9065

Max Act: 22.5315. Min Act: -0.1700

Data Index: 4606090 (The Pile)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 22.9065. Min Range: -22.9065

Max Act: 22.5315. Min Act: -0.1700

Data Index: 563897 (The Pile)

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 22.9065. Min Range: -22.9065

Max Act: 22.5315. Min Act: -0.1700

Data Index: 2053530 (The Pile)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 22.9065. Min Range: -22.9065

Max Act: 22.4065. Min Act: -0.1700

Data Index: 4457216 (The Pile)

Max Activating Token Index: 693

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 22.9065. Min Range: -22.9065

Max Act: 22.4065. Min Act: -0.1700

Data Index: 3847499 (The Pile)

Max Activating Token Index: 539

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 22.9065. Min Range: -22.9065

Max Act: 22.4065. Min Act: -0.1700

Data Index: 6456183 (The Pile)

Max Activating Token Index: 494

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 22.9065. Min Range: -22.9065

Max Act: 22.2815. Min Act: -0.1700

Data Index: 5071170 (The Pile)

Max Activating Token Index: 358

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 22.9065. Min Range: -22.9065

Max Act: 22.1565. Min Act: -0.1700

Data Index: 725074 (The Pile)

Max Activating Token Index: 1008

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 22.9065. Min Range: -22.9065

Max Act: 22.1565. Min Act: -0.1700

Data Index: 1405639 (The Pile)

Max Activating Token Index: 553

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 22.9065. Min Range: -22.9065

Max Act: 22.1565. Min Act: -0.1700

Data Index: 8072133 (The Pile)

Max Activating Token Index: 119

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 22.9065. Min Range: -22.9065

Max Act: 22.1565. Min Act: -0.1700

Data Index: 10623779 (The Pile)

Max Activating Token Index: 1004

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 22.9065. Min Range: -22.9065

Max Act: 22.0315. Min Act: -0.1700

Data Index: 9090605 (The Pile)

Max Activating Token Index: 800

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 22.9065. Min Range: -22.9065

Max Act: 21.7815. Min Act: -0.1700

Data Index: 6266614 (The Pile)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 22.9065. Min Range: -22.9065

Max Act: 21.7815. Min Act: -0.1700

Data Index: 9399773 (The Pile)

Max Activating Token Index: 470

Click toggle to see full text

Truncated

Full Text #19