< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.9758. Min Act: -0.1700

Data Index: 5655515 (The Pile)

Max Activating Token Index: 539

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.9600. Min Act: -0.1700

Data Index: 246572 (The Pile)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.9442. Min Act: -0.1700

Data Index: 231876 (The Pile)

Max Activating Token Index: 450

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.9600. Min Act: -0.1700

Data Index: 4411432 (The Pile)

Max Activating Token Index: 411

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.9125. Min Act: -0.1700

Data Index: 4213276 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.9283. Min Act: -0.1700

Data Index: 1785333 (The Pile)

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.8966. Min Act: -0.1700

Data Index: 2040672 (The Pile)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.9125. Min Act: -0.1700

Data Index: 3967947 (The Pile)

Max Activating Token Index: 598

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.9283. Min Act: -0.1700

Data Index: 6684997 (The Pile)

Max Activating Token Index: 280

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.9283. Min Act: -0.1700

Data Index: 4205366 (The Pile)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.8966. Min Act: -0.1700

Data Index: 10071144 (The Pile)

Max Activating Token Index: 535

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.9125. Min Act: -0.1700

Data Index: 9990025 (The Pile)

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.8966. Min Act: -0.1700

Data Index: 10206619 (The Pile)

Max Activating Token Index: 63

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.9125. Min Act: -0.1700

Data Index: 10141761 (The Pile)

Max Activating Token Index: 488

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.9125. Min Act: -0.1700

Data Index: 9187787 (The Pile)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.8966. Min Act: -0.1700

Data Index: 8628813 (The Pile)

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.9125. Min Act: -0.1700

Data Index: 8326316 (The Pile)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.9125. Min Act: -0.1700

Data Index: 10072395 (The Pile)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.9125. Min Act: -0.1700

Data Index: 2074173 (The Pile)

Max Activating Token Index: 286

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.9125. Min Act: -0.1700

Data Index: 3344616 (The Pile)

Max Activating Token Index: 554

Click toggle to see full text

Truncated

Full Text #19