< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 28 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.0832. Min Range: -4.0832

Max Act: 4.0832. Min Act: -0.1700

Data Index: 1790992 (The Pile)

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.9269. Min Act: -0.1700

Data Index: 2997862 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.7862. Min Act: -0.1700

Data Index: 2063267 (The Pile)

Max Activating Token Index: 109

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.7236. Min Act: -0.1700

Data Index: 9474563 (The Pile)

Max Activating Token Index: 1005

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.7079. Min Act: -0.1700

Data Index: 8648672 (The Pile)

Max Activating Token Index: 334

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.6923. Min Act: -0.1700

Data Index: 862822 (The Pile)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.6766. Min Act: -0.1700

Data Index: 1263184 (The Pile)

Max Activating Token Index: 873

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.6610. Min Act: -0.1700

Data Index: 552585 (The Pile)

Max Activating Token Index: 44

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.6453. Min Act: -0.1700

Data Index: 10406212 (The Pile)

Max Activating Token Index: 257

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.6453. Min Act: -0.1700

Data Index: 10199 (The Pile)

Max Activating Token Index: 487

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.6453. Min Act: -0.1700

Data Index: 6836765 (The Pile)

Max Activating Token Index: 463

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.6453. Min Act: -0.1700

Data Index: 3892086 (The Pile)

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.6453. Min Act: -0.1700

Data Index: 3143122 (The Pile)

Max Activating Token Index: 979

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.6453. Min Act: -0.1700

Data Index: 9366729 (The Pile)

Max Activating Token Index: 474

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.6140. Min Act: -0.1700

Data Index: 8188651 (The Pile)

Max Activating Token Index: 157

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.6140. Min Act: -0.1700

Data Index: 7193200 (The Pile)

Max Activating Token Index: 566

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.5984. Min Act: -0.1700

Data Index: 9545116 (The Pile)

Max Activating Token Index: 714

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.5984. Min Act: -0.1700

Data Index: 30451 (The Pile)

Max Activating Token Index: 642

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.5827. Min Act: -0.1700

Data Index: 6362649 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.0832. Min Range: -4.0832

Max Act: 3.5827. Min Act: -0.1700

Data Index: 6498403 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #19