< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4058 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: 4.4740. Min Range: -4.4740

Max Act: 4.4740. Min Act: -0.1700

Data Index: 9620480 (The Pile)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.4740. Min Range: -4.4740

Max Act: 4.4740. Min Act: -0.1700

Data Index: 1484958 (The Pile)

Max Activating Token Index: 909

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.4740. Min Range: -4.4740

Max Act: 4.4740. Min Act: -0.1700

Data Index: 6932050 (The Pile)

Max Activating Token Index: 360

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.4740. Min Range: -4.4740

Max Act: 4.4428. Min Act: -0.1700

Data Index: 24346 (The Pile)

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.4740. Min Range: -4.4740

Max Act: 4.4428. Min Act: -0.1700

Data Index: 7559954 (The Pile)

Max Activating Token Index: 340

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.4740. Min Range: -4.4740

Max Act: 4.4115. Min Act: -0.1700

Data Index: 10580278 (The Pile)

Max Activating Token Index: 594

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.4740. Min Range: -4.4740

Max Act: 4.4115. Min Act: -0.1700

Data Index: 8571852 (The Pile)

Max Activating Token Index: 289

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.4740. Min Range: -4.4740

Max Act: 4.4115. Min Act: -0.1700

Data Index: 1556192 (The Pile)

Max Activating Token Index: 437

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.4740. Min Range: -4.4740

Max Act: 4.3803. Min Act: -0.1700

Data Index: 4880679 (The Pile)

Max Activating Token Index: 891

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.4740. Min Range: -4.4740

Max Act: 4.3803. Min Act: -0.1700

Data Index: 7735114 (The Pile)

Max Activating Token Index: 702

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.4740. Min Range: -4.4740

Max Act: 4.3803. Min Act: -0.1700

Data Index: 1572221 (The Pile)

Max Activating Token Index: 327

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.4740. Min Range: -4.4740

Max Act: 4.3803. Min Act: -0.1700

Data Index: 7864562 (The Pile)

Max Activating Token Index: 539

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.4740. Min Range: -4.4740

Max Act: 4.3803. Min Act: -0.1700

Data Index: 8760677 (The Pile)

Max Activating Token Index: 728

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.4740. Min Range: -4.4740

Max Act: 4.3803. Min Act: -0.1700

Data Index: 4811637 (The Pile)

Max Activating Token Index: 487

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.4740. Min Range: -4.4740

Max Act: 4.3490. Min Act: -0.1700

Data Index: 8527073 (The Pile)

Max Activating Token Index: 577

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.4740. Min Range: -4.4740

Max Act: 4.3490. Min Act: -0.1700

Data Index: 1372979 (The Pile)

Max Activating Token Index: 445

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.4740. Min Range: -4.4740

Max Act: 4.3490. Min Act: -0.1700

Data Index: 8043299 (The Pile)

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.4740. Min Range: -4.4740

Max Act: 4.3490. Min Act: -0.1700

Data Index: 2525739 (The Pile)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.4740. Min Range: -4.4740

Max Act: 4.3490. Min Act: -0.1700

Data Index: 2335328 (The Pile)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.4740. Min Range: -4.4740

Max Act: 4.3490. Min Act: -0.1700

Data Index: 8667089 (The Pile)

Max Activating Token Index: 329

Click toggle to see full text

Truncated

Full Text #19