< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4090 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.6011. Min Range: -3.6011

Max Act: 3.6011. Min Act: -0.1700

Data Index: 6238698 (The Pile)

Max Activating Token Index: 152

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.6011. Min Range: -3.6011

Max Act: 3.6011. Min Act: -0.1700

Data Index: 953775 (The Pile)

Max Activating Token Index: 597

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.6011. Min Range: -3.6011

Max Act: 3.6011. Min Act: -0.1700

Data Index: 9984945 (The Pile)

Max Activating Token Index: 715

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.6011. Min Range: -3.6011

Max Act: 3.5854. Min Act: -0.1700

Data Index: 5920211 (The Pile)

Max Activating Token Index: 414

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.6011. Min Range: -3.6011

Max Act: 3.5854. Min Act: -0.1700

Data Index: 6545323 (The Pile)

Max Activating Token Index: 460

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.6011. Min Range: -3.6011

Max Act: 3.5385. Min Act: -0.1700

Data Index: 1576628 (The Pile)

Max Activating Token Index: 272

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.6011. Min Range: -3.6011

Max Act: 3.5228. Min Act: -0.1700

Data Index: 2602707 (The Pile)

Max Activating Token Index: 297

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.6011. Min Range: -3.6011

Max Act: 3.5071. Min Act: -0.1700

Data Index: 3205684 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.6011. Min Range: -3.6011

Max Act: 3.4915. Min Act: -0.1700

Data Index: 6372510 (The Pile)

Max Activating Token Index: 629

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.6011. Min Range: -3.6011

Max Act: 3.4915. Min Act: -0.1700

Data Index: 1053555 (The Pile)

Max Activating Token Index: 326

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.6011. Min Range: -3.6011

Max Act: 3.4601. Min Act: -0.1700

Data Index: 5721123 (The Pile)

Max Activating Token Index: 254

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.6011. Min Range: -3.6011

Max Act: 3.4444. Min Act: -0.1700

Data Index: 9110110 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.6011. Min Range: -3.6011

Max Act: 3.4444. Min Act: -0.1700

Data Index: 1958635 (The Pile)

Max Activating Token Index: 326

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.6011. Min Range: -3.6011

Max Act: 3.4131. Min Act: -0.1700

Data Index: 6810 (The Pile)

Max Activating Token Index: 358

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.6011. Min Range: -3.6011

Max Act: 3.4131. Min Act: -0.1700

Data Index: 1030768 (The Pile)

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.6011. Min Range: -3.6011

Max Act: 3.4131. Min Act: -0.1700

Data Index: 3790879 (The Pile)

Max Activating Token Index: 504

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.6011. Min Range: -3.6011

Max Act: 3.4131. Min Act: -0.1700

Data Index: 8744344 (The Pile)

Max Activating Token Index: 729

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.6011. Min Range: -3.6011

Max Act: 3.3974. Min Act: -0.1700

Data Index: 8541502 (The Pile)

Max Activating Token Index: 294

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.6011. Min Range: -3.6011

Max Act: 3.3974. Min Act: -0.1700

Data Index: 4122187 (The Pile)

Max Activating Token Index: 51

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.6011. Min Range: -3.6011

Max Act: 3.3974. Min Act: -0.1700

Data Index: 9187591 (The Pile)

Max Activating Token Index: 326

Click toggle to see full text

Truncated

Full Text #19