< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4066 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.8876. Min Range: -2.8876

Max Act: 2.8876. Min Act: -0.1700

Data Index: 5746016 (The Pile)

Max Activating Token Index: 339

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.8876. Min Range: -2.8876

Max Act: 2.8558. Min Act: -0.1700

Data Index: 5969116 (The Pile)

Max Activating Token Index: 774

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.8876. Min Range: -2.8876

Max Act: 2.8558. Min Act: -0.1700

Data Index: 8741461 (The Pile)

Max Activating Token Index: 918

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.8876. Min Range: -2.8876

Max Act: 2.8081. Min Act: -0.1700

Data Index: 7207432 (The Pile)

Max Activating Token Index: 155

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.8876. Min Range: -2.8876

Max Act: 2.7922. Min Act: -0.1700

Data Index: 8980785 (The Pile)

Max Activating Token Index: 263

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.8876. Min Range: -2.8876

Max Act: 2.7763. Min Act: -0.1700

Data Index: 1970119 (The Pile)

Max Activating Token Index: 166

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.8876. Min Range: -2.8876

Max Act: 2.7763. Min Act: -0.1700

Data Index: 6228529 (The Pile)

Max Activating Token Index: 469

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.8876. Min Range: -2.8876

Max Act: 2.7603. Min Act: -0.1700

Data Index: 5045301 (The Pile)

Max Activating Token Index: 181

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.8876. Min Range: -2.8876

Max Act: 2.7603. Min Act: -0.1700

Data Index: 8850525 (The Pile)

Max Activating Token Index: 317

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.8876. Min Range: -2.8876

Max Act: 2.7603. Min Act: -0.1700

Data Index: 988952 (The Pile)

Max Activating Token Index: 432

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.8876. Min Range: -2.8876

Max Act: 2.7444. Min Act: -0.1700

Data Index: 7381724 (The Pile)

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.8876. Min Range: -2.8876

Max Act: 2.7444. Min Act: -0.1700

Data Index: 396454 (The Pile)

Max Activating Token Index: 292

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.8876. Min Range: -2.8876

Max Act: 2.7284. Min Act: -0.1670

Data Index: 817426 (The Pile)

Max Activating Token Index: 144

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.8876. Min Range: -2.8876

Max Act: 2.7284. Min Act: -0.1700

Data Index: 384946 (The Pile)

Max Activating Token Index: 383

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.8876. Min Range: -2.8876

Max Act: 2.7284. Min Act: -0.1700

Data Index: 8979576 (The Pile)

Max Activating Token Index: 755

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.8876. Min Range: -2.8876

Max Act: 2.7284. Min Act: -0.1700

Data Index: 1139921 (The Pile)

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.8876. Min Range: -2.8876

Max Act: 2.7284. Min Act: -0.1700

Data Index: 4986799 (The Pile)

Max Activating Token Index: 197

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.8876. Min Range: -2.8876

Max Act: 2.7284. Min Act: -0.1700

Data Index: 874855 (The Pile)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.8876. Min Range: -2.8876

Max Act: 2.7284. Min Act: -0.1700

Data Index: 6239324 (The Pile)

Max Activating Token Index: 799

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.8876. Min Range: -2.8876

Max Act: 2.7284. Min Act: -0.1700

Data Index: 3754749 (The Pile)

Max Activating Token Index: 670

Click toggle to see full text

Truncated

Full Text #19