< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 25 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.8210. Min Range: -3.8210

Max Act: 3.6646. Min Act: -0.1700

Data Index: 5813189 (The Pile)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.8210. Min Range: -3.8210

Max Act: 3.6646. Min Act: -0.1700

Data Index: 1580541 (The Pile)

Max Activating Token Index: 758

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.8210. Min Range: -3.8210

Max Act: 3.6020. Min Act: -0.1700

Data Index: 5837989 (The Pile)

Max Activating Token Index: 700

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.8210. Min Range: -3.8210

Max Act: 3.8210. Min Act: -0.1700

Data Index: 6598672 (The Pile)

Max Activating Token Index: 1003

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.8210. Min Range: -3.8210

Max Act: 3.5706. Min Act: -0.1700

Data Index: 10707554 (The Pile)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.8210. Min Range: -3.8210

Max Act: 3.6959. Min Act: -0.1700

Data Index: 4442402 (The Pile)

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.8210. Min Range: -3.8210

Max Act: 3.7585. Min Act: -0.1700

Data Index: 6665992 (The Pile)

Max Activating Token Index: 186

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.8210. Min Range: -3.8210

Max Act: 3.7272. Min Act: -0.1700

Data Index: 5193006 (The Pile)

Max Activating Token Index: 378

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.8210. Min Range: -3.8210

Max Act: 3.6959. Min Act: -0.1700

Data Index: 5664742 (The Pile)

Max Activating Token Index: 643

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.8210. Min Range: -3.8210

Max Act: 3.6646. Min Act: -0.1700

Data Index: 9337451 (The Pile)

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.8210. Min Range: -3.8210

Max Act: 3.6646. Min Act: -0.1700

Data Index: 9381256 (The Pile)

Max Activating Token Index: 122

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.8210. Min Range: -3.8210

Max Act: 3.6020. Min Act: -0.1700

Data Index: 7686038 (The Pile)

Max Activating Token Index: 955

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.8210. Min Range: -3.8210

Max Act: 3.6020. Min Act: -0.1700

Data Index: 8208116 (The Pile)

Max Activating Token Index: 961

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.8210. Min Range: -3.8210

Max Act: 3.6333. Min Act: -0.1700

Data Index: 7358887 (The Pile)

Max Activating Token Index: 363

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.8210. Min Range: -3.8210

Max Act: 3.6959. Min Act: -0.1700

Data Index: 1279995 (The Pile)

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.8210. Min Range: -3.8210

Max Act: 3.5706. Min Act: -0.1700

Data Index: 1252116 (The Pile)

Max Activating Token Index: 574

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.8210. Min Range: -3.8210

Max Act: 3.5393. Min Act: -0.1700

Data Index: 3352919 (The Pile)

Max Activating Token Index: 594

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.8210. Min Range: -3.8210

Max Act: 3.5706. Min Act: -0.1700

Data Index: 9025881 (The Pile)

Max Activating Token Index: 677

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.8210. Min Range: -3.8210

Max Act: 3.4453. Min Act: -0.1700

Data Index: 3127517 (The Pile)

Max Activating Token Index: 898

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.8210. Min Range: -3.8210

Max Act: 3.6959. Min Act: -0.1700

Data Index: 9329839 (The Pile)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #19