< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 50 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.1700

Data Index: 1367 (The Pile)

Max Activating Token Index: 82

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.1700

Data Index: 51 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.1700

Data Index: 1353 (The Pile)

Max Activating Token Index: 180

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.1700

Data Index: 644 (The Pile)

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.1700

Data Index: 1308 (The Pile)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.1700

Data Index: 1272 (The Pile)

Max Activating Token Index: 529

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.1700

Data Index: 291 (The Pile)

Max Activating Token Index: 766

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.1700

Data Index: 1226 (The Pile)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.1700

Data Index: 371 (The Pile)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.1700

Data Index: 372 (The Pile)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.1700

Data Index: 805 (The Pile)

Max Activating Token Index: 130

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.1700

Data Index: 1155 (The Pile)

Max Activating Token Index: 213

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.1700

Data Index: 1106 (The Pile)

Max Activating Token Index: 841

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.1700

Data Index: 1077 (The Pile)

Max Activating Token Index: 241

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.1700

Data Index: 1071 (The Pile)

Max Activating Token Index: 693

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.1700

Data Index: 1398 (The Pile)

Max Activating Token Index: 641

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.1700

Data Index: 1039 (The Pile)

Max Activating Token Index: 901

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.1700

Data Index: 664 (The Pile)

Max Activating Token Index: 32

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.1700

Data Index: 146 (The Pile)

Max Activating Token Index: 573

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.8185. Min Range: -1.8185

Max Act: 1.8185. Min Act: -0.1700

Data Index: 816 (The Pile)

Max Activating Token Index: 728

Click toggle to see full text

Truncated

Full Text #19