< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 27 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')



Text #0

Max Range: 1.1057. Min Range: -1.1057

Max Act: 1.1057. Min Act: -0.1643

Data Index: 173636 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.9147. Min Act: -0.1687

Data Index: 1746483 (Open Web Text)

Max Activating Token Index: 794

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8805. Min Act: -0.1671

Data Index: 6006488 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8465. Min Act: -0.1643

Data Index: 2216471 (Open Web Text)

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8296. Min Act: -0.1643

Data Index: 5692410 (Open Web Text)

Max Activating Token Index: 787

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8127. Min Act: -0.1643

Data Index: 3956913 (Open Web Text)

Max Activating Token Index: 778

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7792. Min Act: -0.1643

Data Index: 7434568 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7792. Min Act: -0.1693

Data Index: 3883650 (Open Web Text)

Max Activating Token Index: 807

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7626. Min Act: -0.1643

Data Index: 6831605 (Open Web Text)

Max Activating Token Index: 805

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7460. Min Act: -0.1643

Data Index: 6220861 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7460. Min Act: -0.1696

Data Index: 7686985 (Open Web Text)

Max Activating Token Index: 756

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7460. Min Act: -0.1643

Data Index: 8450396 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7295. Min Act: -0.1643

Data Index: 6726578 (Open Web Text)

Max Activating Token Index: 749

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7131. Min Act: -0.1700

Data Index: 942671 (Open Web Text)

Max Activating Token Index: 822

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7131. Min Act: -0.1643

Data Index: 8227766 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7131. Min Act: -0.1677

Data Index: 6308436 (Open Web Text)

Max Activating Token Index: 699

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.6805. Min Act: -0.1643

Data Index: 704272 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.6643. Min Act: -0.1699

Data Index: 8245251 (Open Web Text)

Max Activating Token Index: 866

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.6643. Min Act: -0.1643

Data Index: 6643798 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.6967. Min Act: -0.1643

Data Index: 7883518 (Open Web Text)

Max Activating Token Index: 279

Click toggle to see full text

Truncated

Full Text #19