< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 48 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: 3.0721. Min Range: -3.0721

Max Act: 3.0721. Min Act: -0.1700

Data Index: 1432626 (The Pile)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.0721. Min Range: -3.0721

Max Act: 3.0405. Min Act: -0.1700

Data Index: 7691265 (The Pile)

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.0721. Min Range: -3.0721

Max Act: 3.0089. Min Act: -0.1700

Data Index: 2278655 (The Pile)

Max Activating Token Index: 636

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.0721. Min Range: -3.0721

Max Act: 2.9931. Min Act: -0.1700

Data Index: 651468 (The Pile)

Max Activating Token Index: 704

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.0721. Min Range: -3.0721

Max Act: 2.9615. Min Act: -0.1700

Data Index: 10494052 (The Pile)

Max Activating Token Index: 611

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.0721. Min Range: -3.0721

Max Act: 2.9457. Min Act: -0.1700

Data Index: 9736699 (The Pile)

Max Activating Token Index: 250

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.0721. Min Range: -3.0721

Max Act: 2.9298. Min Act: -0.1700

Data Index: 7305711 (The Pile)

Max Activating Token Index: 932

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.0721. Min Range: -3.0721

Max Act: 2.9298. Min Act: -0.1700

Data Index: 1990400 (The Pile)

Max Activating Token Index: 707

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.0721. Min Range: -3.0721

Max Act: 2.9298. Min Act: -0.1700

Data Index: 3883767 (The Pile)

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.0721. Min Range: -3.0721

Max Act: 2.9140. Min Act: -0.1700

Data Index: 1354549 (The Pile)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.0721. Min Range: -3.0721

Max Act: 2.9140. Min Act: -0.1700

Data Index: 9880633 (The Pile)

Max Activating Token Index: 841

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.0721. Min Range: -3.0721

Max Act: 2.9140. Min Act: -0.1700

Data Index: 783377 (The Pile)

Max Activating Token Index: 944

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.0721. Min Range: -3.0721

Max Act: 2.8981. Min Act: -0.1700

Data Index: 5634572 (The Pile)

Max Activating Token Index: 775

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.0721. Min Range: -3.0721

Max Act: 2.8981. Min Act: -0.1700

Data Index: 3535459 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.0721. Min Range: -3.0721

Max Act: 2.8822. Min Act: -0.1700

Data Index: 9725791 (The Pile)

Max Activating Token Index: 871

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.0721. Min Range: -3.0721

Max Act: 2.8822. Min Act: -0.1700

Data Index: 7872452 (The Pile)

Max Activating Token Index: 973

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.0721. Min Range: -3.0721

Max Act: 2.8822. Min Act: -0.1700

Data Index: 3662127 (The Pile)

Max Activating Token Index: 964

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.0721. Min Range: -3.0721

Max Act: 2.8664. Min Act: -0.1700

Data Index: 3600764 (The Pile)

Max Activating Token Index: 725

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.0721. Min Range: -3.0721

Max Act: 2.8664. Min Act: -0.1700

Data Index: 3996803 (The Pile)

Max Activating Token Index: 642

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.0721. Min Range: -3.0721

Max Act: 2.8664. Min Act: -0.1700

Data Index: 2821051 (The Pile)

Max Activating Token Index: 546

Click toggle to see full text

Truncated

Full Text #19