< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6393 in Layer 41

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 7.4610. Min Range: -7.4610

Max Act: 7.4610. Min Act: -0.1700

Data Index: 405478 (Open Web Text)

Max Activating Token Index: 541

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 7.4610. Min Range: -7.4610

Max Act: 7.3672. Min Act: -0.1700

Data Index: 1971315 (Open Web Text)

Max Activating Token Index: 824

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 7.4610. Min Range: -7.4610

Max Act: 7.2735. Min Act: -0.1700

Data Index: 7329149 (Open Web Text)

Max Activating Token Index: 797

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 7.4610. Min Range: -7.4610

Max Act: 7.1797. Min Act: -0.1700

Data Index: 2933620 (Open Web Text)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 7.4610. Min Range: -7.4610

Max Act: 7.0860. Min Act: -0.1700

Data Index: 8685122 (Open Web Text)

Max Activating Token Index: 856

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 7.4610. Min Range: -7.4610

Max Act: 6.8360. Min Act: -0.1700

Data Index: 8458097 (Open Web Text)

Max Activating Token Index: 179

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 7.4610. Min Range: -7.4610

Max Act: 6.8360. Min Act: -0.1700

Data Index: 5813835 (Open Web Text)

Max Activating Token Index: 824

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 7.4610. Min Range: -7.4610

Max Act: 6.8360. Min Act: -0.1700

Data Index: 2849637 (Open Web Text)

Max Activating Token Index: 577

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 7.4610. Min Range: -7.4610

Max Act: 6.8047. Min Act: -0.1700

Data Index: 3722307 (Open Web Text)

Max Activating Token Index: 880

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 7.4610. Min Range: -7.4610

Max Act: 6.8360. Min Act: -0.1700

Data Index: 3188163 (Open Web Text)

Max Activating Token Index: 730

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 7.4610. Min Range: -7.4610

Max Act: 6.7735. Min Act: -0.1700

Data Index: 4320730 (Open Web Text)

Max Activating Token Index: 60

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 7.4610. Min Range: -7.4610

Max Act: 6.7735. Min Act: -0.1700

Data Index: 4703567 (Open Web Text)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 7.4610. Min Range: -7.4610

Max Act: 6.7422. Min Act: -0.1700

Data Index: 4560770 (Open Web Text)

Max Activating Token Index: 660

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 7.4610. Min Range: -7.4610

Max Act: 6.7422. Min Act: -0.1700

Data Index: 1300454 (Open Web Text)

Max Activating Token Index: 391

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 7.4610. Min Range: -7.4610

Max Act: 6.7422. Min Act: -0.1700

Data Index: 1155756 (Open Web Text)

Max Activating Token Index: 308

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 7.4610. Min Range: -7.4610

Max Act: 6.7110. Min Act: -0.1700

Data Index: 7923971 (Open Web Text)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 7.4610. Min Range: -7.4610

Max Act: 6.6797. Min Act: -0.1700

Data Index: 4839623 (Open Web Text)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 7.4610. Min Range: -7.4610

Max Act: 6.6797. Min Act: -0.1700

Data Index: 127662 (Open Web Text)

Max Activating Token Index: 249

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 7.4610. Min Range: -7.4610

Max Act: 6.6797. Min Act: -0.1700

Data Index: 1621365 (Open Web Text)

Max Activating Token Index: 532

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 7.4610. Min Range: -7.4610

Max Act: 6.6797. Min Act: -0.1700

Data Index: 4379399 (Open Web Text)

Max Activating Token Index: 613

Click toggle to see full text

Truncated

Full Text #19