< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 8 in Layer 22

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 5.2920. Min Range: -5.2920

Max Act: 5.2920. Min Act: -0.1696

Data Index: 475157 (The Pile)

Max Activating Token Index: 970

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.2920. Min Range: -5.2920

Max Act: 5.2295. Min Act: -0.1694

Data Index: 1287282 (The Pile)

Max Activating Token Index: 726

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.2920. Min Range: -5.2920

Max Act: 5.1045. Min Act: -0.1698

Data Index: 3170568 (The Pile)

Max Activating Token Index: 389

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.2920. Min Range: -5.2920

Max Act: 5.0420. Min Act: -0.1700

Data Index: 2564024 (The Pile)

Max Activating Token Index: 820

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.2920. Min Range: -5.2920

Max Act: 5.0420. Min Act: -0.1686

Data Index: 9354181 (The Pile)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.2920. Min Range: -5.2920

Max Act: 5.0420. Min Act: -0.1684

Data Index: 9222926 (The Pile)

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.2920. Min Range: -5.2920

Max Act: 5.0420. Min Act: -0.1699

Data Index: 6077110 (The Pile)

Max Activating Token Index: 609

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.2920. Min Range: -5.2920

Max Act: 5.0108. Min Act: -0.1700

Data Index: 7084702 (The Pile)

Max Activating Token Index: 973

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.2920. Min Range: -5.2920

Max Act: 5.0108. Min Act: -0.1698

Data Index: 8126481 (The Pile)

Max Activating Token Index: 666

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.2920. Min Range: -5.2920

Max Act: 5.0108. Min Act: -0.1699

Data Index: 8251796 (The Pile)

Max Activating Token Index: 591

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.2920. Min Range: -5.2920

Max Act: 5.0108. Min Act: -0.1698

Data Index: 9343386 (The Pile)

Max Activating Token Index: 973

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.2920. Min Range: -5.2920

Max Act: 5.0108. Min Act: -0.1700

Data Index: 1155800 (The Pile)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.2920. Min Range: -5.2920

Max Act: 5.0108. Min Act: -0.1699

Data Index: 5763772 (The Pile)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.2920. Min Range: -5.2920

Max Act: 5.0108. Min Act: -0.1700

Data Index: 6977572 (The Pile)

Max Activating Token Index: 489

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.2920. Min Range: -5.2920

Max Act: 5.0108. Min Act: -0.1678

Data Index: 9947643 (The Pile)

Max Activating Token Index: 907

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.9795. Min Act: -0.1696

Data Index: 1643843 (The Pile)

Max Activating Token Index: 934

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.9795. Min Act: -0.1700

Data Index: 7004959 (The Pile)

Max Activating Token Index: 518

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.9795. Min Act: -0.1700

Data Index: 2865573 (The Pile)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.9795. Min Act: -0.1681

Data Index: 3654088 (The Pile)

Max Activating Token Index: 499

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.2920. Min Range: -5.2920

Max Act: 4.9795. Min Act: -0.1699

Data Index: 811100 (The Pile)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #19