< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4038 in Layer 16

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.5389. Min Act: -0.1700

Data Index: 1499053 (The Pile)

Max Activating Token Index: 855

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.5389. Min Act: -0.1700

Data Index: 2048537 (The Pile)

Max Activating Token Index: 156

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.5233. Min Act: -0.1700

Data Index: 9861903 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.5076. Min Act: -0.1700

Data Index: 1242799 (The Pile)

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.5076. Min Act: -0.1700

Data Index: 505447 (The Pile)

Max Activating Token Index: 681

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.5076. Min Act: -0.1700

Data Index: 1708788 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4763. Min Act: -0.1700

Data Index: 10535271 (The Pile)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4606. Min Act: -0.1700

Data Index: 2794227 (The Pile)

Max Activating Token Index: 752

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4606. Min Act: -0.1700

Data Index: 8019038 (The Pile)

Max Activating Token Index: 528

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4606. Min Act: -0.1700

Data Index: 9015357 (The Pile)

Max Activating Token Index: 871

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4449. Min Act: -0.1700

Data Index: 978853 (The Pile)

Max Activating Token Index: 392

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4449. Min Act: -0.1700

Data Index: 3629938 (The Pile)

Max Activating Token Index: 138

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4292. Min Act: -0.1700

Data Index: 4827854 (The Pile)

Max Activating Token Index: 372

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4292. Min Act: -0.1700

Data Index: 8530368 (The Pile)

Max Activating Token Index: 138

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4136. Min Act: -0.1700

Data Index: 9401297 (The Pile)

Max Activating Token Index: 1010

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4136. Min Act: -0.1700

Data Index: 10662801 (The Pile)

Max Activating Token Index: 849

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4136. Min Act: -0.1700

Data Index: 4416808 (The Pile)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.3979. Min Act: -0.1700

Data Index: 3182589 (The Pile)

Max Activating Token Index: 164

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.3979. Min Act: -0.1700

Data Index: 7600846 (The Pile)

Max Activating Token Index: 946

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.3979. Min Act: -0.1700

Data Index: 1402020 (The Pile)

Max Activating Token Index: 653

Click toggle to see full text

Truncated

Full Text #19