< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 3 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 2.5904. Min Range: -2.5904

Max Act: 2.5904. Min Act: -0.1699

Data Index: 9417669 (The Pile)

Max Activating Token Index: 569

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.5904. Min Range: -2.5904

Max Act: 2.3633. Min Act: -0.1700

Data Index: 10318580 (The Pile)

Max Activating Token Index: 57

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.5904. Min Range: -2.5904

Max Act: 2.1986. Min Act: -0.1700

Data Index: 4281500 (The Pile)

Max Activating Token Index: 175

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.5904. Min Range: -2.5904

Max Act: 2.1820. Min Act: -0.1699

Data Index: 5089612 (The Pile)

Max Activating Token Index: 253

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.5904. Min Range: -2.5904

Max Act: 2.1820. Min Act: -0.1699

Data Index: 5147422 (The Pile)

Max Activating Token Index: 822

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.5904. Min Range: -2.5904

Max Act: 2.1654. Min Act: -0.1700

Data Index: 10579156 (The Pile)

Max Activating Token Index: 889

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.5904. Min Range: -2.5904

Max Act: 2.1654. Min Act: -0.1700

Data Index: 9705227 (The Pile)

Max Activating Token Index: 211

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.5904. Min Range: -2.5904

Max Act: 2.1487. Min Act: -0.1699

Data Index: 7033842 (The Pile)

Max Activating Token Index: 514

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.5904. Min Range: -2.5904

Max Act: 2.1487. Min Act: -0.1700

Data Index: 4646461 (The Pile)

Max Activating Token Index: 331

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.5904. Min Range: -2.5904

Max Act: 2.1487. Min Act: -0.1700

Data Index: 201173 (The Pile)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.5904. Min Range: -2.5904

Max Act: 2.1320. Min Act: -0.1700

Data Index: 6536469 (The Pile)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.5904. Min Range: -2.5904

Max Act: 2.1153. Min Act: -0.1700

Data Index: 3563928 (The Pile)

Max Activating Token Index: 306

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.5904. Min Range: -2.5904

Max Act: 2.1320. Min Act: -0.1700

Data Index: 9222860 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.5904. Min Range: -2.5904

Max Act: 2.1320. Min Act: -0.1700

Data Index: 2846677 (The Pile)

Max Activating Token Index: 205

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.5904. Min Range: -2.5904

Max Act: 2.1153. Min Act: -0.1700

Data Index: 3914162 (The Pile)

Max Activating Token Index: 222

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.5904. Min Range: -2.5904

Max Act: 2.1153. Min Act: -0.1700

Data Index: 8498530 (The Pile)

Max Activating Token Index: 605

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.5904. Min Range: -2.5904

Max Act: 2.1153. Min Act: -0.1700

Data Index: 4833716 (The Pile)

Max Activating Token Index: 430

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.5904. Min Range: -2.5904

Max Act: 2.0986. Min Act: -0.1699

Data Index: 1507759 (The Pile)

Max Activating Token Index: 1011

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.5904. Min Range: -2.5904

Max Act: 2.1153. Min Act: -0.1700

Data Index: 9187391 (The Pile)

Max Activating Token Index: 1014

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.5904. Min Range: -2.5904

Max Act: 2.0986. Min Act: -0.1700

Data Index: 9309128 (The Pile)

Max Activating Token Index: 995

Click toggle to see full text

Truncated

Full Text #19