< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 41 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 3.2371. Min Range: -3.2371

Max Act: 3.2371. Min Act: -0.1700

Data Index: 104306 (The Pile)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2371. Min Range: -3.2371

Max Act: 3.2057. Min Act: -0.1700

Data Index: 5474464 (The Pile)

Max Activating Token Index: 314

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2371. Min Range: -3.2371

Max Act: 3.2057. Min Act: -0.1700

Data Index: 4502459 (The Pile)

Max Activating Token Index: 800

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2371. Min Range: -3.2371

Max Act: 3.1899. Min Act: -0.1700

Data Index: 7176230 (The Pile)

Max Activating Token Index: 267

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2371. Min Range: -3.2371

Max Act: 3.1742. Min Act: -0.1700

Data Index: 34294 (The Pile)

Max Activating Token Index: 222

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2371. Min Range: -3.2371

Max Act: 3.1742. Min Act: -0.1700

Data Index: 2491962 (The Pile)

Max Activating Token Index: 202

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2371. Min Range: -3.2371

Max Act: 3.1742. Min Act: -0.1700

Data Index: 6418981 (The Pile)

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2371. Min Range: -3.2371

Max Act: 3.1742. Min Act: -0.1700

Data Index: 5210746 (The Pile)

Max Activating Token Index: 823

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2371. Min Range: -3.2371

Max Act: 3.1585. Min Act: -0.1700

Data Index: 9094506 (The Pile)

Max Activating Token Index: 938

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2371. Min Range: -3.2371

Max Act: 3.1585. Min Act: -0.1700

Data Index: 4251750 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2371. Min Range: -3.2371

Max Act: 3.1427. Min Act: -0.1700

Data Index: 10047151 (The Pile)

Max Activating Token Index: 666

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2371. Min Range: -3.2371

Max Act: 3.1427. Min Act: -0.1700

Data Index: 2853573 (The Pile)

Max Activating Token Index: 593

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2371. Min Range: -3.2371

Max Act: 3.1427. Min Act: -0.1700

Data Index: 10410825 (The Pile)

Max Activating Token Index: 444

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2371. Min Range: -3.2371

Max Act: 3.1427. Min Act: -0.1700

Data Index: 2881541 (The Pile)

Max Activating Token Index: 112

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2371. Min Range: -3.2371

Max Act: 3.1269. Min Act: -0.1700

Data Index: 9719125 (The Pile)

Max Activating Token Index: 860

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2371. Min Range: -3.2371

Max Act: 3.1269. Min Act: -0.1700

Data Index: 8756907 (The Pile)

Max Activating Token Index: 320

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2371. Min Range: -3.2371

Max Act: 3.1269. Min Act: -0.1700

Data Index: 6685072 (The Pile)

Max Activating Token Index: 609

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2371. Min Range: -3.2371

Max Act: 3.1269. Min Act: -0.1700

Data Index: 2693642 (The Pile)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2371. Min Range: -3.2371

Max Act: 3.1112. Min Act: -0.1700

Data Index: 4708121 (The Pile)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2371. Min Range: -3.2371

Max Act: 3.1112. Min Act: -0.1700

Data Index: 4276105 (The Pile)

Max Activating Token Index: 627

Click toggle to see full text

Truncated

Full Text #19