< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4087 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.7891. Min Range: -1.7891

Max Act: 1.7891. Min Act: -0.1700

Data Index: 82 (The Pile)

Max Activating Token Index: 129

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.7891. Min Range: -1.7891

Max Act: 1.7891. Min Act: -0.1700

Data Index: 1050 (The Pile)

Max Activating Token Index: 700

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.7891. Min Range: -1.7891

Max Act: 1.7891. Min Act: -0.1700

Data Index: 673 (The Pile)

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.7891. Min Range: -1.7891

Max Act: 1.7891. Min Act: -0.1700

Data Index: 892 (The Pile)

Max Activating Token Index: 528

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.7891. Min Range: -1.7891

Max Act: 1.7891. Min Act: -0.1700

Data Index: 958 (The Pile)

Max Activating Token Index: 762

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.7891. Min Range: -1.7891

Max Act: 1.7891. Min Act: -0.1700

Data Index: 334 (The Pile)

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.7891. Min Range: -1.7891

Max Act: 1.7891. Min Act: -0.1700

Data Index: 154 (The Pile)

Max Activating Token Index: 899

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.7891. Min Range: -1.7891

Max Act: 1.7891. Min Act: -0.1700

Data Index: 770 (The Pile)

Max Activating Token Index: 317

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.7891. Min Range: -1.7891

Max Act: 1.7891. Min Act: -0.1700

Data Index: 35 (The Pile)

Max Activating Token Index: 714

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.7891. Min Range: -1.7891

Max Act: 1.7891. Min Act: -0.1700

Data Index: 446 (The Pile)

Max Activating Token Index: 725

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.7891. Min Range: -1.7891

Max Act: 1.7891. Min Act: -0.1700

Data Index: 773 (The Pile)

Max Activating Token Index: 571

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.7891. Min Range: -1.7891

Max Act: 1.7891. Min Act: -0.1700

Data Index: 227 (The Pile)

Max Activating Token Index: 853

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.7891. Min Range: -1.7891

Max Act: 1.7891. Min Act: -0.1700

Data Index: 564 (The Pile)

Max Activating Token Index: 313

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.7891. Min Range: -1.7891

Max Act: 1.7891. Min Act: -0.1700

Data Index: 463 (The Pile)

Max Activating Token Index: 993

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.7891. Min Range: -1.7891

Max Act: 1.7891. Min Act: -0.1700

Data Index: 538 (The Pile)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.7891. Min Range: -1.7891

Max Act: 1.7891. Min Act: -0.1700

Data Index: 429 (The Pile)

Max Activating Token Index: 295

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.7891. Min Range: -1.7891

Max Act: 1.7891. Min Act: -0.1700

Data Index: 416 (The Pile)

Max Activating Token Index: 810

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.7891. Min Range: -1.7891

Max Act: 1.7891. Min Act: -0.1700

Data Index: 707 (The Pile)

Max Activating Token Index: 179

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.7891. Min Range: -1.7891

Max Act: 1.7891. Min Act: -0.1700

Data Index: 523 (The Pile)

Max Activating Token Index: 848

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.7891. Min Range: -1.7891

Max Act: 1.7891. Min Act: -0.1700

Data Index: 122 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #19