< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 70 in Layer 12

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.2769. Min Range: -3.2769

Max Act: 3.2769. Min Act: -0.1700

Data Index: 8516498 (The Pile)

Max Activating Token Index: 474

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2769. Min Range: -3.2769

Max Act: 2.8665. Min Act: -0.1700

Data Index: 605623 (The Pile)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2769. Min Range: -3.2769

Max Act: 2.8506. Min Act: -0.1700

Data Index: 7293990 (The Pile)

Max Activating Token Index: 376

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2769. Min Range: -3.2769

Max Act: 2.8347. Min Act: -0.1700

Data Index: 4338759 (The Pile)

Max Activating Token Index: 330

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2769. Min Range: -3.2769

Max Act: 2.8188. Min Act: -0.1700

Data Index: 9809631 (The Pile)

Max Activating Token Index: 252

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2769. Min Range: -3.2769

Max Act: 2.8188. Min Act: -0.1700

Data Index: 10692747 (The Pile)

Max Activating Token Index: 880

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2769. Min Range: -3.2769

Max Act: 2.8188. Min Act: -0.1700

Data Index: 2444812 (The Pile)

Max Activating Token Index: 930

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2769. Min Range: -3.2769

Max Act: 2.8188. Min Act: -0.1700

Data Index: 1822954 (The Pile)

Max Activating Token Index: 452

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2769. Min Range: -3.2769

Max Act: 2.8188. Min Act: -0.1700

Data Index: 6577312 (The Pile)

Max Activating Token Index: 289

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2769. Min Range: -3.2769

Max Act: 2.8029. Min Act: -0.1700

Data Index: 3954435 (The Pile)

Max Activating Token Index: 636

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2769. Min Range: -3.2769

Max Act: 2.8029. Min Act: -0.1700

Data Index: 3756693 (The Pile)

Max Activating Token Index: 673

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2769. Min Range: -3.2769

Max Act: 2.8029. Min Act: -0.1700

Data Index: 61474 (The Pile)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2769. Min Range: -3.2769

Max Act: 2.8029. Min Act: -0.1700

Data Index: 1854010 (The Pile)

Max Activating Token Index: 630

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2769. Min Range: -3.2769

Max Act: 2.8029. Min Act: -0.1700

Data Index: 3385155 (The Pile)

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2769. Min Range: -3.2769

Max Act: 2.7869. Min Act: -0.1700

Data Index: 7122709 (The Pile)

Max Activating Token Index: 306

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2769. Min Range: -3.2769

Max Act: 2.7869. Min Act: -0.1700

Data Index: 6562752 (The Pile)

Max Activating Token Index: 67

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2769. Min Range: -3.2769

Max Act: 2.7869. Min Act: -0.1700

Data Index: 872549 (The Pile)

Max Activating Token Index: 784

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2769. Min Range: -3.2769

Max Act: 2.7869. Min Act: -0.1700

Data Index: 7389155 (The Pile)

Max Activating Token Index: 303

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2769. Min Range: -3.2769

Max Act: 2.7869. Min Act: -0.1700

Data Index: 6441351 (The Pile)

Max Activating Token Index: 664

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2769. Min Range: -3.2769

Max Act: 2.7869. Min Act: -0.1700

Data Index: 7527869 (The Pile)

Max Activating Token Index: 1003

Click toggle to see full text

Truncated

Full Text #19