< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6377 in Layer 40

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 11.7805. Min Range: -11.7805

Max Act: 11.7805. Min Act: -0.1700

Data Index: 4553531 (Open Web Text)

Max Activating Token Index: 418

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 11.7805. Min Range: -11.7805

Max Act: 11.4680. Min Act: -0.1700

Data Index: 6659970 (Open Web Text)

Max Activating Token Index: 219

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 11.7805. Min Range: -11.7805

Max Act: 11.4680. Min Act: -0.1700

Data Index: 4978993 (Open Web Text)

Max Activating Token Index: 366

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 11.7805. Min Range: -11.7805

Max Act: 11.4680. Min Act: -0.1700

Data Index: 7810796 (Open Web Text)

Max Activating Token Index: 252

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 11.7805. Min Range: -11.7805

Max Act: 11.4680. Min Act: -0.1700

Data Index: 1736017 (Open Web Text)

Max Activating Token Index: 593

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 11.7805. Min Range: -11.7805

Max Act: 11.3430. Min Act: -0.1700

Data Index: 1201450 (Open Web Text)

Max Activating Token Index: 65

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 11.7805. Min Range: -11.7805

Max Act: 11.2805. Min Act: -0.1700

Data Index: 4395909 (Open Web Text)

Max Activating Token Index: 470

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 11.7805. Min Range: -11.7805

Max Act: 11.2180. Min Act: -0.1700

Data Index: 5647416 (Open Web Text)

Max Activating Token Index: 952

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 11.7805. Min Range: -11.7805

Max Act: 11.1555. Min Act: -0.1700

Data Index: 7442366 (Open Web Text)

Max Activating Token Index: 930

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 11.7805. Min Range: -11.7805

Max Act: 11.1555. Min Act: -0.1700

Data Index: 8286011 (Open Web Text)

Max Activating Token Index: 881

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 11.7805. Min Range: -11.7805

Max Act: 11.1555. Min Act: -0.1700

Data Index: 2504228 (Open Web Text)

Max Activating Token Index: 515

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 11.7805. Min Range: -11.7805

Max Act: 11.1555. Min Act: -0.1700

Data Index: 1915133 (Open Web Text)

Max Activating Token Index: 130

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 11.7805. Min Range: -11.7805

Max Act: 11.2180. Min Act: -0.1700

Data Index: 5335573 (Open Web Text)

Max Activating Token Index: 427

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 11.7805. Min Range: -11.7805

Max Act: 11.0930. Min Act: -0.1700

Data Index: 4085136 (Open Web Text)

Max Activating Token Index: 816

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 11.7805. Min Range: -11.7805

Max Act: 11.0930. Min Act: -0.1700

Data Index: 8335993 (Open Web Text)

Max Activating Token Index: 836

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 11.7805. Min Range: -11.7805

Max Act: 11.0305. Min Act: -0.1700

Data Index: 2530635 (Open Web Text)

Max Activating Token Index: 660

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 11.7805. Min Range: -11.7805

Max Act: 11.0305. Min Act: -0.1700

Data Index: 5501020 (Open Web Text)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 11.7805. Min Range: -11.7805

Max Act: 10.9680. Min Act: -0.1700

Data Index: 7794894 (Open Web Text)

Max Activating Token Index: 584

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 11.7805. Min Range: -11.7805

Max Act: 10.9680. Min Act: -0.1700

Data Index: 6230004 (Open Web Text)

Max Activating Token Index: 416

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 11.7805. Min Range: -11.7805

Max Act: 10.9055. Min Act: -0.1700

Data Index: 4958074 (Open Web Text)

Max Activating Token Index: 445

Click toggle to see full text

Truncated

Full Text #19