< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4090 in Layer 13

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.1449. Min Range: -3.1449

Max Act: 3.1449. Min Act: -0.1700

Data Index: 1400205 (The Pile)

Max Activating Token Index: 992

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.1449. Min Range: -3.1449

Max Act: 3.1134. Min Act: -0.1700

Data Index: 10785475 (The Pile)

Max Activating Token Index: 909

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.1449. Min Range: -3.1449

Max Act: 3.0819. Min Act: -0.1700

Data Index: 1060128 (The Pile)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.1449. Min Range: -3.1449

Max Act: 3.0345. Min Act: -0.1700

Data Index: 10575220 (The Pile)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.1449. Min Range: -3.1449

Max Act: 3.0187. Min Act: -0.1700

Data Index: 8413017 (The Pile)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.1449. Min Range: -3.1449

Max Act: 3.0187. Min Act: -0.1700

Data Index: 7226404 (The Pile)

Max Activating Token Index: 203

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.1449. Min Range: -3.1449

Max Act: 3.0029. Min Act: -0.1700

Data Index: 9519155 (The Pile)

Max Activating Token Index: 484

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9871. Min Act: -0.1700

Data Index: 3436737 (The Pile)

Max Activating Token Index: 875

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9713. Min Act: -0.1700

Data Index: 9891941 (The Pile)

Max Activating Token Index: 328

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9555. Min Act: -0.1700

Data Index: 1211270 (The Pile)

Max Activating Token Index: 797

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9555. Min Act: -0.1700

Data Index: 7825474 (The Pile)

Max Activating Token Index: 313

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9555. Min Act: -0.1700

Data Index: 7132579 (The Pile)

Max Activating Token Index: 256

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9555. Min Act: -0.1700

Data Index: 5283396 (The Pile)

Max Activating Token Index: 1006

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9396. Min Act: -0.1700

Data Index: 1324217 (The Pile)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9238. Min Act: -0.1700

Data Index: 5252740 (The Pile)

Max Activating Token Index: 242

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9238. Min Act: -0.1700

Data Index: 8077606 (The Pile)

Max Activating Token Index: 916

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9238. Min Act: -0.1700

Data Index: 3811919 (The Pile)

Max Activating Token Index: 624

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9238. Min Act: -0.1700

Data Index: 697444 (The Pile)

Max Activating Token Index: 150

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9238. Min Act: -0.1700

Data Index: 4317551 (The Pile)

Max Activating Token Index: 330

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.1449. Min Range: -3.1449

Max Act: 2.9079. Min Act: -0.1700

Data Index: 8497986 (The Pile)

Max Activating Token Index: 775

Click toggle to see full text

Truncated

Full Text #19