< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 46 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.1060. Min Range: -4.1060

Max Act: 4.1060. Min Act: -0.1700

Data Index: 589864 (The Pile)

Max Activating Token Index: 826

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.7151. Min Act: -0.1700

Data Index: 7316670 (The Pile)

Max Activating Token Index: 273

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.7776. Min Act: -0.1700

Data Index: 3804555 (The Pile)

Max Activating Token Index: 866

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.8089. Min Act: -0.1700

Data Index: 5332255 (The Pile)

Max Activating Token Index: 1014

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.6994. Min Act: -0.1700

Data Index: 3561743 (The Pile)

Max Activating Token Index: 815

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.7151. Min Act: -0.1700

Data Index: 9805602 (The Pile)

Max Activating Token Index: 715

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.6212. Min Act: -0.1700

Data Index: 5995907 (The Pile)

Max Activating Token Index: 547

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.6681. Min Act: -0.1700

Data Index: 5430860 (The Pile)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.7307. Min Act: -0.1700

Data Index: 3049333 (The Pile)

Max Activating Token Index: 600

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.6212. Min Act: -0.1700

Data Index: 6909679 (The Pile)

Max Activating Token Index: 683

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.6525. Min Act: -0.1700

Data Index: 3668666 (The Pile)

Max Activating Token Index: 574

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.6681. Min Act: -0.1700

Data Index: 285308 (The Pile)

Max Activating Token Index: 340

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.5742. Min Act: -0.1700

Data Index: 62053 (The Pile)

Max Activating Token Index: 837

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.6681. Min Act: -0.1700

Data Index: 2963891 (The Pile)

Max Activating Token Index: 42

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.6055. Min Act: -0.1700

Data Index: 10759512 (The Pile)

Max Activating Token Index: 945

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.6368. Min Act: -0.1700

Data Index: 6899011 (The Pile)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.6055. Min Act: -0.1700

Data Index: 4751051 (The Pile)

Max Activating Token Index: 814

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.6212. Min Act: -0.1700

Data Index: 3618667 (The Pile)

Max Activating Token Index: 566

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.6212. Min Act: -0.1700

Data Index: 2910437 (The Pile)

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.1060. Min Range: -4.1060

Max Act: 3.5742. Min Act: -0.1700

Data Index: 174917 (The Pile)

Max Activating Token Index: 843

Click toggle to see full text

Truncated

Full Text #19