< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 72 in Layer 43

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 10.2399. Min Range: -10.2399

Max Act: 10.2399. Min Act: -0.1700

Data Index: 1945637 (Open Web Text)

Max Activating Token Index: 579

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.2399. Min Range: -10.2399

Max Act: 10.1774. Min Act: -0.1700

Data Index: 6832761 (Open Web Text)

Max Activating Token Index: 706

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.2399. Min Range: -10.2399

Max Act: 10.0524. Min Act: -0.1700

Data Index: 317758 (Open Web Text)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.2399. Min Range: -10.2399

Max Act: 10.1149. Min Act: -0.1700

Data Index: 80448 (Open Web Text)

Max Activating Token Index: 1004

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.2399. Min Range: -10.2399

Max Act: 10.0524. Min Act: -0.1700

Data Index: 2841042 (Open Web Text)

Max Activating Token Index: 1000

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.2399. Min Range: -10.2399

Max Act: 9.9899. Min Act: -0.1700

Data Index: 3930112 (Open Web Text)

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.2399. Min Range: -10.2399

Max Act: 9.8649. Min Act: -0.1700

Data Index: 1279559 (Open Web Text)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.2399. Min Range: -10.2399

Max Act: 9.8024. Min Act: -0.1700

Data Index: 3623404 (Open Web Text)

Max Activating Token Index: 838

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.2399. Min Range: -10.2399

Max Act: 9.8024. Min Act: -0.1700

Data Index: 6415898 (Open Web Text)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.2399. Min Range: -10.2399

Max Act: 9.7399. Min Act: -0.1700

Data Index: 5749871 (Open Web Text)

Max Activating Token Index: 744

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.2399. Min Range: -10.2399

Max Act: 9.6774. Min Act: -0.1700

Data Index: 66422 (Open Web Text)

Max Activating Token Index: 73

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.2399. Min Range: -10.2399

Max Act: 9.6774. Min Act: -0.1700

Data Index: 6846746 (Open Web Text)

Max Activating Token Index: 479

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.2399. Min Range: -10.2399

Max Act: 9.6774. Min Act: -0.1700

Data Index: 4190923 (Open Web Text)

Max Activating Token Index: 335

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.2399. Min Range: -10.2399

Max Act: 9.6149. Min Act: -0.1700

Data Index: 8164942 (Open Web Text)

Max Activating Token Index: 397

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.2399. Min Range: -10.2399

Max Act: 9.6149. Min Act: -0.1700

Data Index: 1745611 (Open Web Text)

Max Activating Token Index: 444

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.2399. Min Range: -10.2399

Max Act: 9.6774. Min Act: -0.1700

Data Index: 3308229 (Open Web Text)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.2399. Min Range: -10.2399

Max Act: 9.4899. Min Act: -0.1700

Data Index: 300802 (Open Web Text)

Max Activating Token Index: 443

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.2399. Min Range: -10.2399

Max Act: 9.5524. Min Act: -0.1700

Data Index: 1678577 (Open Web Text)

Max Activating Token Index: 392

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.2399. Min Range: -10.2399

Max Act: 9.5524. Min Act: -0.1700

Data Index: 5863893 (Open Web Text)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.2399. Min Range: -10.2399

Max Act: 9.4899. Min Act: -0.1700

Data Index: 5072016 (Open Web Text)

Max Activating Token Index: 688

Click toggle to see full text

Truncated

Full Text #19