< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4043 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: 3.0554. Min Range: -3.0554

Max Act: 3.0554. Min Act: -0.1700

Data Index: 5495421 (The Pile)

Max Activating Token Index: 26

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.0554. Min Range: -3.0554

Max Act: 2.9606. Min Act: -0.1700

Data Index: 3812113 (The Pile)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.0554. Min Range: -3.0554

Max Act: 2.9606. Min Act: -0.1700

Data Index: 4631834 (The Pile)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.0554. Min Range: -3.0554

Max Act: 2.9606. Min Act: -0.1700

Data Index: 6784324 (The Pile)

Max Activating Token Index: 134

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.0554. Min Range: -3.0554

Max Act: 2.9448. Min Act: -0.1700

Data Index: 4231875 (The Pile)

Max Activating Token Index: 331

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.0554. Min Range: -3.0554

Max Act: 2.9289. Min Act: -0.1700

Data Index: 6558299 (The Pile)

Max Activating Token Index: 357

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.0554. Min Range: -3.0554

Max Act: 2.9289. Min Act: -0.1700

Data Index: 9687739 (The Pile)

Max Activating Token Index: 203

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.0554. Min Range: -3.0554

Max Act: 2.9289. Min Act: -0.1700

Data Index: 1887509 (The Pile)

Max Activating Token Index: 370

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.0554. Min Range: -3.0554

Max Act: 2.9289. Min Act: -0.1700

Data Index: 4422958 (The Pile)

Max Activating Token Index: 889

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.0554. Min Range: -3.0554

Max Act: 2.9131. Min Act: -0.1700

Data Index: 2466174 (The Pile)

Max Activating Token Index: 87

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.0554. Min Range: -3.0554

Max Act: 2.8813. Min Act: -0.1700

Data Index: 8844975 (The Pile)

Max Activating Token Index: 66

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.0554. Min Range: -3.0554

Max Act: 2.8813. Min Act: -0.1700

Data Index: 9640372 (The Pile)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.0554. Min Range: -3.0554

Max Act: 2.8813. Min Act: -0.1700

Data Index: 7975829 (The Pile)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.0554. Min Range: -3.0554

Max Act: 2.8813. Min Act: -0.1700

Data Index: 7692639 (The Pile)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.0554. Min Range: -3.0554

Max Act: 2.8813. Min Act: -0.1700

Data Index: 6429739 (The Pile)

Max Activating Token Index: 884

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.0554. Min Range: -3.0554

Max Act: 2.8655. Min Act: -0.1700

Data Index: 6734801 (The Pile)

Max Activating Token Index: 735

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.0554. Min Range: -3.0554

Max Act: 2.8655. Min Act: -0.1700

Data Index: 4724197 (The Pile)

Max Activating Token Index: 594

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.0554. Min Range: -3.0554

Max Act: 2.8655. Min Act: -0.1700

Data Index: 4428586 (The Pile)

Max Activating Token Index: 189

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.0554. Min Range: -3.0554

Max Act: 2.8655. Min Act: -0.1700

Data Index: 8701100 (The Pile)

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.0554. Min Range: -3.0554

Max Act: 2.8655. Min Act: -0.1700

Data Index: 7040456 (The Pile)

Max Activating Token Index: 609

Click toggle to see full text

Truncated

Full Text #19