< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 45 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 5.3716. Min Range: -5.3716

Max Act: 5.3404. Min Act: -0.1700

Data Index: 674065 (The Pile)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.3716. Min Range: -5.3716

Max Act: 5.3716. Min Act: -0.1700

Data Index: 6491002 (The Pile)

Max Activating Token Index: 733

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.3716. Min Range: -5.3716

Max Act: 5.3091. Min Act: -0.1700

Data Index: 1436220 (The Pile)

Max Activating Token Index: 225

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.3716. Min Range: -5.3716

Max Act: 5.2466. Min Act: -0.1700

Data Index: 6895436 (The Pile)

Max Activating Token Index: 868

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.3716. Min Range: -5.3716

Max Act: 5.3404. Min Act: -0.1700

Data Index: 5592816 (The Pile)

Max Activating Token Index: 861

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.3716. Min Range: -5.3716

Max Act: 5.2466. Min Act: -0.1700

Data Index: 8549693 (The Pile)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.3716. Min Range: -5.3716

Max Act: 5.3091. Min Act: -0.1700

Data Index: 3558291 (The Pile)

Max Activating Token Index: 683

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.3716. Min Range: -5.3716

Max Act: 5.1841. Min Act: -0.1700

Data Index: 7062731 (The Pile)

Max Activating Token Index: 758

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.3716. Min Range: -5.3716

Max Act: 5.1841. Min Act: -0.1700

Data Index: 1664662 (The Pile)

Max Activating Token Index: 813

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.3716. Min Range: -5.3716

Max Act: 5.1841. Min Act: -0.1700

Data Index: 10431255 (The Pile)

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.3716. Min Range: -5.3716

Max Act: 5.2466. Min Act: -0.1700

Data Index: 1933060 (The Pile)

Max Activating Token Index: 854

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.3716. Min Range: -5.3716

Max Act: 5.2466. Min Act: -0.1686

Data Index: 5906196 (The Pile)

Max Activating Token Index: 501

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.3716. Min Range: -5.3716

Max Act: 5.0591. Min Act: -0.1700

Data Index: 9812491 (The Pile)

Max Activating Token Index: 393

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.3716. Min Range: -5.3716

Max Act: 5.2466. Min Act: -0.1700

Data Index: 1516028 (The Pile)

Max Activating Token Index: 573

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.3716. Min Range: -5.3716

Max Act: 5.2154. Min Act: -0.1700

Data Index: 10143264 (The Pile)

Max Activating Token Index: 993

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.3716. Min Range: -5.3716

Max Act: 5.3091. Min Act: -0.1700

Data Index: 5840787 (The Pile)

Max Activating Token Index: 911

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.3716. Min Range: -5.3716

Max Act: 5.0904. Min Act: -0.1700

Data Index: 2795047 (The Pile)

Max Activating Token Index: 741

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.3716. Min Range: -5.3716

Max Act: 5.1529. Min Act: -0.1700

Data Index: 5423482 (The Pile)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.3716. Min Range: -5.3716

Max Act: 5.1216. Min Act: -0.1639

Data Index: 1772347 (The Pile)

Max Activating Token Index: 619

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.3716. Min Range: -5.3716

Max Act: 5.0279. Min Act: -0.1700

Data Index: 4952239 (The Pile)

Max Activating Token Index: 325

Click toggle to see full text

Truncated

Full Text #19