< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4026 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: 3.1048. Min Range: -3.1048

Max Act: 3.1048. Min Act: -0.1699

Data Index: 7877231 (The Pile)

Max Activating Token Index: 843

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.1048. Min Range: -3.1048

Max Act: 3.1048. Min Act: -0.1700

Data Index: 4927697 (The Pile)

Max Activating Token Index: 907

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.1048. Min Range: -3.1048

Max Act: 3.0890. Min Act: -0.1700

Data Index: 6473130 (The Pile)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.1048. Min Range: -3.1048

Max Act: 3.0733. Min Act: -0.1700

Data Index: 9649610 (The Pile)

Max Activating Token Index: 532

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.1048. Min Range: -3.1048

Max Act: 3.0733. Min Act: -0.1700

Data Index: 2948857 (The Pile)

Max Activating Token Index: 297

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.1048. Min Range: -3.1048

Max Act: 3.0259. Min Act: -0.1699

Data Index: 7171144 (The Pile)

Max Activating Token Index: 507

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.1048. Min Range: -3.1048

Max Act: 3.0259. Min Act: -0.1700

Data Index: 5428332 (The Pile)

Max Activating Token Index: 922

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.1048. Min Range: -3.1048

Max Act: 3.0259. Min Act: -0.1699

Data Index: 8340031 (The Pile)

Max Activating Token Index: 302

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.1048. Min Range: -3.1048

Max Act: 3.0259. Min Act: -0.1700

Data Index: 4750518 (The Pile)

Max Activating Token Index: 512

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.1048. Min Range: -3.1048

Max Act: 3.0101. Min Act: -0.1700

Data Index: 6913343 (The Pile)

Max Activating Token Index: 199

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.1048. Min Range: -3.1048

Max Act: 3.0101. Min Act: -0.1700

Data Index: 6450591 (The Pile)

Max Activating Token Index: 291

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.1048. Min Range: -3.1048

Max Act: 3.0101. Min Act: -0.1700

Data Index: 6227358 (The Pile)

Max Activating Token Index: 88

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.1048. Min Range: -3.1048

Max Act: 3.0101. Min Act: -0.1700

Data Index: 10121840 (The Pile)

Max Activating Token Index: 122

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.1048. Min Range: -3.1048

Max Act: 2.9943. Min Act: -0.1700

Data Index: 1929965 (The Pile)

Max Activating Token Index: 571

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.1048. Min Range: -3.1048

Max Act: 2.9943. Min Act: -0.1700

Data Index: 9919947 (The Pile)

Max Activating Token Index: 357

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.1048. Min Range: -3.1048

Max Act: 2.9785. Min Act: -0.1700

Data Index: 3116623 (The Pile)

Max Activating Token Index: 916

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.1048. Min Range: -3.1048

Max Act: 2.9785. Min Act: -0.1700

Data Index: 3686160 (The Pile)

Max Activating Token Index: 519

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.1048. Min Range: -3.1048

Max Act: 2.9785. Min Act: -0.1700

Data Index: 6807338 (The Pile)

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.1048. Min Range: -3.1048

Max Act: 2.9785. Min Act: -0.1700

Data Index: 7895753 (The Pile)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.1048. Min Range: -3.1048

Max Act: 2.9785. Min Act: -0.1700

Data Index: 3103178 (The Pile)

Max Activating Token Index: 944

Click toggle to see full text

Truncated

Full Text #19