< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 46 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.5724. Min Range: -2.5724

Max Act: 2.5724. Min Act: -0.1700

Data Index: 4404254 (The Pile)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.5724. Min Range: -2.5724

Max Act: 2.5563. Min Act: -0.1700

Data Index: 1969793 (The Pile)

Max Activating Token Index: 895

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.5724. Min Range: -2.5724

Max Act: 2.5240. Min Act: -0.1700

Data Index: 6476721 (The Pile)

Max Activating Token Index: 670

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.5724. Min Range: -2.5724

Max Act: 2.5078. Min Act: -0.1700

Data Index: 2028395 (The Pile)

Max Activating Token Index: 350

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.5724. Min Range: -2.5724

Max Act: 2.4754. Min Act: -0.1700

Data Index: 4891994 (The Pile)

Max Activating Token Index: 329

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.5724. Min Range: -2.5724

Max Act: 2.4754. Min Act: -0.1700

Data Index: 9681723 (The Pile)

Max Activating Token Index: 170

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.5724. Min Range: -2.5724

Max Act: 2.4754. Min Act: -0.1700

Data Index: 6160232 (The Pile)

Max Activating Token Index: 94

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.5724. Min Range: -2.5724

Max Act: 2.4754. Min Act: -0.1700

Data Index: 2546748 (The Pile)

Max Activating Token Index: 919

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.5724. Min Range: -2.5724

Max Act: 2.4754. Min Act: -0.1700

Data Index: 3610552 (The Pile)

Max Activating Token Index: 861

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.5724. Min Range: -2.5724

Max Act: 2.4591. Min Act: -0.1700

Data Index: 957633 (The Pile)

Max Activating Token Index: 692

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.5724. Min Range: -2.5724

Max Act: 2.4591. Min Act: -0.1700

Data Index: 6514081 (The Pile)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.5724. Min Range: -2.5724

Max Act: 2.4429. Min Act: -0.1700

Data Index: 3088859 (The Pile)

Max Activating Token Index: 498

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.5724. Min Range: -2.5724

Max Act: 2.4429. Min Act: -0.1700

Data Index: 6411556 (The Pile)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.5724. Min Range: -2.5724

Max Act: 2.4429. Min Act: -0.1700

Data Index: 1618795 (The Pile)

Max Activating Token Index: 251

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.5724. Min Range: -2.5724

Max Act: 2.4429. Min Act: -0.1700

Data Index: 8160440 (The Pile)

Max Activating Token Index: 1004

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.5724. Min Range: -2.5724

Max Act: 2.4266. Min Act: -0.1700

Data Index: 3737434 (The Pile)

Max Activating Token Index: 787

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.5724. Min Range: -2.5724

Max Act: 2.4266. Min Act: -0.1700

Data Index: 2457134 (The Pile)

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.5724. Min Range: -2.5724

Max Act: 2.4266. Min Act: -0.1700

Data Index: 4161389 (The Pile)

Max Activating Token Index: 746

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.5724. Min Range: -2.5724

Max Act: 2.4266. Min Act: -0.1700

Data Index: 6452913 (The Pile)

Max Activating Token Index: 489

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.5724. Min Range: -2.5724

Max Act: 2.4266. Min Act: -0.1700

Data Index: 2028047 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #19