< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 70 in Layer 22

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 5.0836. Min Range: -5.0836

Max Act: 5.0524. Min Act: -0.1700

Data Index: 5294929 (Open Web Text)

Max Activating Token Index: 358

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.0836. Min Range: -5.0836

Max Act: 5.0836. Min Act: -0.1700

Data Index: 5313207 (Open Web Text)

Max Activating Token Index: 304

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.0836. Min Range: -5.0836

Max Act: 5.0211. Min Act: -0.1700

Data Index: 7361753 (Open Web Text)

Max Activating Token Index: 896

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.0836. Min Range: -5.0836

Max Act: 4.9899. Min Act: -0.1700

Data Index: 8077138 (Open Web Text)

Max Activating Token Index: 788

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.0836. Min Range: -5.0836

Max Act: 4.9899. Min Act: -0.1700

Data Index: 6728793 (Open Web Text)

Max Activating Token Index: 410

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.0836. Min Range: -5.0836

Max Act: 4.9586. Min Act: -0.1700

Data Index: 860684 (Open Web Text)

Max Activating Token Index: 740

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.0836. Min Range: -5.0836

Max Act: 4.9274. Min Act: -0.1700

Data Index: 4235136 (Open Web Text)

Max Activating Token Index: 527

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.0836. Min Range: -5.0836

Max Act: 4.8961. Min Act: -0.1700

Data Index: 7041140 (Open Web Text)

Max Activating Token Index: 233

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.0836. Min Range: -5.0836

Max Act: 4.8649. Min Act: -0.1700

Data Index: 4947676 (Open Web Text)

Max Activating Token Index: 830

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.0836. Min Range: -5.0836

Max Act: 4.8336. Min Act: -0.1700

Data Index: 7596558 (Open Web Text)

Max Activating Token Index: 328

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.0836. Min Range: -5.0836

Max Act: 4.8336. Min Act: -0.1700

Data Index: 8248899 (Open Web Text)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.0836. Min Range: -5.0836

Max Act: 4.8024. Min Act: -0.1700

Data Index: 3284544 (Open Web Text)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.0836. Min Range: -5.0836

Max Act: 4.8024. Min Act: -0.1700

Data Index: 3583032 (Open Web Text)

Max Activating Token Index: 894

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.0836. Min Range: -5.0836

Max Act: 4.7399. Min Act: -0.1700

Data Index: 7616067 (Open Web Text)

Max Activating Token Index: 170

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.0836. Min Range: -5.0836

Max Act: 4.7711. Min Act: -0.1700

Data Index: 7676599 (Open Web Text)

Max Activating Token Index: 308

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.0836. Min Range: -5.0836

Max Act: 4.7711. Min Act: -0.1700

Data Index: 6261799 (Open Web Text)

Max Activating Token Index: 337

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.0836. Min Range: -5.0836

Max Act: 4.7399. Min Act: -0.1700

Data Index: 1707818 (Open Web Text)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.0836. Min Range: -5.0836

Max Act: 4.7399. Min Act: -0.1700

Data Index: 6268704 (Open Web Text)

Max Activating Token Index: 102

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.0836. Min Range: -5.0836

Max Act: 4.7399. Min Act: -0.1700

Data Index: 4072683 (Open Web Text)

Max Activating Token Index: 376

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.0836. Min Range: -5.0836

Max Act: 4.7399. Min Act: -0.1700

Data Index: 1426357 (Open Web Text)

Max Activating Token Index: 791

Click toggle to see full text

Truncated

Full Text #19