< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 6 in Layer 19

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.2273. Min Range: -3.2273

Max Act: 3.2273. Min Act: -0.1700

Data Index: 7378033 (The Pile)

Max Activating Token Index: 708

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2273. Min Range: -3.2273

Max Act: 3.2116. Min Act: -0.1700

Data Index: 3591712 (The Pile)

Max Activating Token Index: 889

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2273. Min Range: -3.2273

Max Act: 3.1013. Min Act: -0.1700

Data Index: 7310007 (The Pile)

Max Activating Token Index: 151

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2273. Min Range: -3.2273

Max Act: 3.1013. Min Act: -0.1700

Data Index: 6820187 (The Pile)

Max Activating Token Index: 130

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2273. Min Range: -3.2273

Max Act: 3.0856. Min Act: -0.1700

Data Index: 9485208 (The Pile)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2273. Min Range: -3.2273

Max Act: 3.0698. Min Act: -0.1700

Data Index: 5932918 (The Pile)

Max Activating Token Index: 866

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2273. Min Range: -3.2273

Max Act: 3.0540. Min Act: -0.1700

Data Index: 3600895 (The Pile)

Max Activating Token Index: 421

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2273. Min Range: -3.2273

Max Act: 3.0382. Min Act: -0.1700

Data Index: 7911660 (The Pile)

Max Activating Token Index: 415

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2273. Min Range: -3.2273

Max Act: 3.0382. Min Act: -0.1700

Data Index: 9344562 (The Pile)

Max Activating Token Index: 163

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2273. Min Range: -3.2273

Max Act: 3.0382. Min Act: -0.1700

Data Index: 308660 (The Pile)

Max Activating Token Index: 340

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2273. Min Range: -3.2273

Max Act: 3.0382. Min Act: -0.1700

Data Index: 140050 (The Pile)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2273. Min Range: -3.2273

Max Act: 3.0224. Min Act: -0.1700

Data Index: 1017620 (The Pile)

Max Activating Token Index: 144

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2273. Min Range: -3.2273

Max Act: 3.0224. Min Act: -0.1700

Data Index: 444717 (The Pile)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2273. Min Range: -3.2273

Max Act: 3.0066. Min Act: -0.1700

Data Index: 3477969 (The Pile)

Max Activating Token Index: 68

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2273. Min Range: -3.2273

Max Act: 3.0066. Min Act: -0.1700

Data Index: 7376358 (The Pile)

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2273. Min Range: -3.2273

Max Act: 2.9908. Min Act: -0.1700

Data Index: 10489085 (The Pile)

Max Activating Token Index: 585

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2273. Min Range: -3.2273

Max Act: 2.9908. Min Act: -0.1700

Data Index: 8955793 (The Pile)

Max Activating Token Index: 854

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2273. Min Range: -3.2273

Max Act: 2.9908. Min Act: -0.1700

Data Index: 6800752 (The Pile)

Max Activating Token Index: 729

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2273. Min Range: -3.2273

Max Act: 2.9750. Min Act: -0.1700

Data Index: 1296327 (The Pile)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2273. Min Range: -3.2273

Max Act: 2.9750. Min Act: -0.1700

Data Index: 2649637 (The Pile)

Max Activating Token Index: 882

Click toggle to see full text

Truncated

Full Text #19