< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 27 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.9104. Min Act: -0.1700

Data Index: 7473217 (The Pile)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.7227. Min Act: -0.1700

Data Index: 1027468 (The Pile)

Max Activating Token Index: 566

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.6915. Min Act: -0.1700

Data Index: 5085283 (The Pile)

Max Activating Token Index: 213

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.6915. Min Act: -0.1700

Data Index: 127719 (The Pile)

Max Activating Token Index: 660

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.6915. Min Act: -0.1700

Data Index: 1501769 (The Pile)

Max Activating Token Index: 498

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.6758. Min Act: -0.1700

Data Index: 1004734 (The Pile)

Max Activating Token Index: 746

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.6758. Min Act: -0.1700

Data Index: 3290557 (The Pile)

Max Activating Token Index: 684

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.6758. Min Act: -0.1700

Data Index: 7739112 (The Pile)

Max Activating Token Index: 631

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.6758. Min Act: -0.1700

Data Index: 8852451 (The Pile)

Max Activating Token Index: 393

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.6602. Min Act: -0.1700

Data Index: 6899710 (The Pile)

Max Activating Token Index: 788

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.6602. Min Act: -0.1700

Data Index: 4751317 (The Pile)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.6602. Min Act: -0.1700

Data Index: 135832 (The Pile)

Max Activating Token Index: 1009

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.6602. Min Act: -0.1700

Data Index: 8471510 (The Pile)

Max Activating Token Index: 836

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.6602. Min Act: -0.1700

Data Index: 4197279 (The Pile)

Max Activating Token Index: 610

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.6602. Min Act: -0.1700

Data Index: 5351764 (The Pile)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.6445. Min Act: -0.1700

Data Index: 1313519 (The Pile)

Max Activating Token Index: 1018

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.6445. Min Act: -0.1700

Data Index: 4392905 (The Pile)

Max Activating Token Index: 586

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.6445. Min Act: -0.1700

Data Index: 4503016 (The Pile)

Max Activating Token Index: 500

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.6445. Min Act: -0.1700

Data Index: 2201786 (The Pile)

Max Activating Token Index: 918

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.6445. Min Act: -0.1700

Data Index: 5108183 (The Pile)

Max Activating Token Index: 415

Click toggle to see full text

Truncated

Full Text #19