< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2032 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.4905. Min Range: -4.4905

Max Act: 4.4905. Min Act: -0.1700

Data Index: 4953236 (The Pile)

Max Activating Token Index: 898

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.4905. Min Range: -4.4905

Max Act: 4.4905. Min Act: -0.1700

Data Index: 762374 (The Pile)

Max Activating Token Index: 937

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.4905. Min Range: -4.4905

Max Act: 4.4593. Min Act: -0.1700

Data Index: 2773617 (The Pile)

Max Activating Token Index: 673

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.4905. Min Range: -4.4905

Max Act: 4.4593. Min Act: -0.1700

Data Index: 1705864 (The Pile)

Max Activating Token Index: 558

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.4905. Min Range: -4.4905

Max Act: 4.4593. Min Act: -0.1700

Data Index: 8721585 (The Pile)

Max Activating Token Index: 191

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.4905. Min Range: -4.4905

Max Act: 4.4280. Min Act: -0.1700

Data Index: 3769015 (The Pile)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.4905. Min Range: -4.4905

Max Act: 4.4280. Min Act: -0.1700

Data Index: 8054707 (The Pile)

Max Activating Token Index: 866

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.4905. Min Range: -4.4905

Max Act: 4.4280. Min Act: -0.1700

Data Index: 6838635 (The Pile)

Max Activating Token Index: 881

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.4905. Min Range: -4.4905

Max Act: 4.4280. Min Act: -0.1700

Data Index: 1325708 (The Pile)

Max Activating Token Index: 370

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.4905. Min Range: -4.4905

Max Act: 4.4280. Min Act: -0.1700

Data Index: 6757778 (The Pile)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.4905. Min Range: -4.4905

Max Act: 4.4280. Min Act: -0.1700

Data Index: 5140739 (The Pile)

Max Activating Token Index: 333

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.4905. Min Range: -4.4905

Max Act: 4.4280. Min Act: -0.1700

Data Index: 790110 (The Pile)

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.4905. Min Range: -4.4905

Max Act: 4.4280. Min Act: -0.1700

Data Index: 4137911 (The Pile)

Max Activating Token Index: 590

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.4905. Min Range: -4.4905

Max Act: 4.4280. Min Act: -0.1700

Data Index: 1910439 (The Pile)

Max Activating Token Index: 898

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.4905. Min Range: -4.4905

Max Act: 4.4280. Min Act: -0.1700

Data Index: 3304384 (The Pile)

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.4905. Min Range: -4.4905

Max Act: 4.4280. Min Act: -0.1700

Data Index: 3180426 (The Pile)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.4905. Min Range: -4.4905

Max Act: 4.4280. Min Act: -0.1700

Data Index: 2814256 (The Pile)

Max Activating Token Index: 960

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.4905. Min Range: -4.4905

Max Act: 4.4280. Min Act: -0.1700

Data Index: 984018 (The Pile)

Max Activating Token Index: 742

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.4905. Min Range: -4.4905

Max Act: 4.4280. Min Act: -0.1700

Data Index: 2801296 (The Pile)

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.4905. Min Range: -4.4905

Max Act: 4.4280. Min Act: -0.1700

Data Index: 2690394 (The Pile)

Max Activating Token Index: 865

Click toggle to see full text

Truncated

Full Text #19