< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4076 in Layer 14

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.4605. Min Range: -3.4605

Max Act: 3.4605. Min Act: -0.1700

Data Index: 8818977 (The Pile)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.4605. Min Range: -3.4605

Max Act: 3.4605. Min Act: -0.1700

Data Index: 6772838 (The Pile)

Max Activating Token Index: 721

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.4605. Min Range: -3.4605

Max Act: 3.4448. Min Act: -0.1700

Data Index: 1488156 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.4605. Min Range: -3.4605

Max Act: 3.4448. Min Act: -0.1700

Data Index: 7274589 (The Pile)

Max Activating Token Index: 794

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.4605. Min Range: -3.4605

Max Act: 3.4291. Min Act: -0.1700

Data Index: 9512258 (The Pile)

Max Activating Token Index: 573

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.4605. Min Range: -3.4605

Max Act: 3.3977. Min Act: -0.1700

Data Index: 1118756 (The Pile)

Max Activating Token Index: 881

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.4605. Min Range: -3.4605

Max Act: 3.3977. Min Act: -0.1700

Data Index: 3112391 (The Pile)

Max Activating Token Index: 93

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.4605. Min Range: -3.4605

Max Act: 3.3821. Min Act: -0.1700

Data Index: 297090 (The Pile)

Max Activating Token Index: 400

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.4605. Min Range: -3.4605

Max Act: 3.3821. Min Act: -0.1700

Data Index: 6249366 (The Pile)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.4605. Min Range: -3.4605

Max Act: 3.3821. Min Act: -0.1700

Data Index: 7392986 (The Pile)

Max Activating Token Index: 195

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.4605. Min Range: -3.4605

Max Act: 3.3821. Min Act: -0.1700

Data Index: 4285380 (The Pile)

Max Activating Token Index: 490

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.4605. Min Range: -3.4605

Max Act: 3.3664. Min Act: -0.1700

Data Index: 3249160 (The Pile)

Max Activating Token Index: 475

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.4605. Min Range: -3.4605

Max Act: 3.3664. Min Act: -0.1700

Data Index: 405564 (The Pile)

Max Activating Token Index: 920

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.4605. Min Range: -3.4605

Max Act: 3.3664. Min Act: -0.1700

Data Index: 9907795 (The Pile)

Max Activating Token Index: 531

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.4605. Min Range: -3.4605

Max Act: 3.3507. Min Act: -0.1700

Data Index: 5019917 (The Pile)

Max Activating Token Index: 338

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.4605. Min Range: -3.4605

Max Act: 3.3507. Min Act: -0.1700

Data Index: 7427457 (The Pile)

Max Activating Token Index: 873

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.4605. Min Range: -3.4605

Max Act: 3.3507. Min Act: -0.1700

Data Index: 7426905 (The Pile)

Max Activating Token Index: 934

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.4605. Min Range: -3.4605

Max Act: 3.3507. Min Act: -0.1700

Data Index: 796611 (The Pile)

Max Activating Token Index: 714

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.4605. Min Range: -3.4605

Max Act: 3.3507. Min Act: -0.1700

Data Index: 7917287 (The Pile)

Max Activating Token Index: 889

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.4605. Min Range: -3.4605

Max Act: 3.3507. Min Act: -0.1700

Data Index: 8549017 (The Pile)

Max Activating Token Index: 604

Click toggle to see full text

Truncated

Full Text #19