< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 3057 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 44.6013. Min Range: -44.6013

Max Act: 44.6013. Min Act: -0.1691

Data Index: 3134840 (The Pile)

Max Activating Token Index: 825

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 44.6013. Min Range: -44.6013

Max Act: 43.3513. Min Act: -0.1700

Data Index: 10475983 (The Pile)

Max Activating Token Index: 686

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 44.6013. Min Range: -44.6013

Max Act: 43.3513. Min Act: -0.1700

Data Index: 10411951 (The Pile)

Max Activating Token Index: 873

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 44.6013. Min Range: -44.6013

Max Act: 43.3513. Min Act: -0.1700

Data Index: 7818740 (The Pile)

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 44.6013. Min Range: -44.6013

Max Act: 43.1013. Min Act: -0.1697

Data Index: 9663155 (The Pile)

Max Activating Token Index: 988

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 44.6013. Min Range: -44.6013

Max Act: 43.1013. Min Act: -0.1700

Data Index: 4460869 (The Pile)

Max Activating Token Index: 767

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 44.6013. Min Range: -44.6013

Max Act: 42.6013. Min Act: -0.1700

Data Index: 6776738 (The Pile)

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 44.6013. Min Range: -44.6013

Max Act: 42.3513. Min Act: -0.1700

Data Index: 4786442 (The Pile)

Max Activating Token Index: 977

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 44.6013. Min Range: -44.6013

Max Act: 42.3513. Min Act: -0.1700

Data Index: 722975 (The Pile)

Max Activating Token Index: 649

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 44.6013. Min Range: -44.6013

Max Act: 42.3513. Min Act: -0.1700

Data Index: 2746339 (The Pile)

Max Activating Token Index: 693

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 44.6013. Min Range: -44.6013

Max Act: 42.1013. Min Act: -0.1700

Data Index: 4628934 (The Pile)

Max Activating Token Index: 805

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 44.6013. Min Range: -44.6013

Max Act: 42.1013. Min Act: -0.1700

Data Index: 4063604 (The Pile)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 44.6013. Min Range: -44.6013

Max Act: 42.1013. Min Act: -0.1692

Data Index: 4840957 (The Pile)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 44.6013. Min Range: -44.6013

Max Act: 42.1013. Min Act: -0.1700

Data Index: 8320568 (The Pile)

Max Activating Token Index: 1018

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 44.6013. Min Range: -44.6013

Max Act: 41.8513. Min Act: -0.1699

Data Index: 7372369 (The Pile)

Max Activating Token Index: 856

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 44.6013. Min Range: -44.6013

Max Act: 41.8513. Min Act: -0.1697

Data Index: 2568424 (The Pile)

Max Activating Token Index: 299

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 44.6013. Min Range: -44.6013

Max Act: 41.8513. Min Act: -0.1697

Data Index: 5337873 (The Pile)

Max Activating Token Index: 945

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 44.6013. Min Range: -44.6013

Max Act: 41.6013. Min Act: -0.1697

Data Index: 1672412 (The Pile)

Max Activating Token Index: 831

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 44.6013. Min Range: -44.6013

Max Act: 41.6013. Min Act: -0.1700

Data Index: 9185334 (The Pile)

Max Activating Token Index: 855

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 44.6013. Min Range: -44.6013

Max Act: 41.6013. Min Act: -0.1700

Data Index: 3243421 (The Pile)

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #19