< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2004 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.1700

Data Index: 1828 (The Pile)

Max Activating Token Index: 509

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.1699

Data Index: 3778 (The Pile)

Max Activating Token Index: 502

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.1699

Data Index: 3734 (The Pile)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.1700

Data Index: 326 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.1700

Data Index: 2877 (The Pile)

Max Activating Token Index: 442

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.1700

Data Index: 3569 (The Pile)

Max Activating Token Index: 782

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.1700

Data Index: 2284 (The Pile)

Max Activating Token Index: 779

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.1697

Data Index: 2279 (The Pile)

Max Activating Token Index: 241

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.1700

Data Index: 2234 (The Pile)

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.1700

Data Index: 1970 (The Pile)

Max Activating Token Index: 824

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.1700

Data Index: 675 (The Pile)

Max Activating Token Index: 554

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.1700

Data Index: 1723 (The Pile)

Max Activating Token Index: 414

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.1700

Data Index: 1412 (The Pile)

Max Activating Token Index: 80

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.1700

Data Index: 3476 (The Pile)

Max Activating Token Index: 198

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.1700

Data Index: 1264 (The Pile)

Max Activating Token Index: 171

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.1700

Data Index: 1228 (The Pile)

Max Activating Token Index: 882

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.1700

Data Index: 1152 (The Pile)

Max Activating Token Index: 211

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.1700

Data Index: 125 (The Pile)

Max Activating Token Index: 194

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.1700

Data Index: 1109 (The Pile)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.1700

Data Index: 1050 (The Pile)

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #19