< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6380 in Layer 32

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 10.1901. Min Range: -10.1901

Max Act: 10.1901. Min Act: -0.1700

Data Index: 6927085 (Open Web Text)

Max Activating Token Index: 899

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.1901. Min Range: -10.1901

Max Act: 9.3776. Min Act: -0.1700

Data Index: 7710544 (Open Web Text)

Max Activating Token Index: 994

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.1901. Min Range: -10.1901

Max Act: 9.3151. Min Act: -0.1700

Data Index: 2022463 (Open Web Text)

Max Activating Token Index: 839

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.1901. Min Range: -10.1901

Max Act: 9.3151. Min Act: -0.1700

Data Index: 8438978 (Open Web Text)

Max Activating Token Index: 233

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.1901. Min Range: -10.1901

Max Act: 9.3151. Min Act: -0.1700

Data Index: 1431410 (Open Web Text)

Max Activating Token Index: 331

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.1901. Min Range: -10.1901

Max Act: 9.2526. Min Act: -0.1700

Data Index: 2666959 (Open Web Text)

Max Activating Token Index: 171

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.1901. Min Range: -10.1901

Max Act: 9.2526. Min Act: -0.1700

Data Index: 3267823 (Open Web Text)

Max Activating Token Index: 598

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.1901. Min Range: -10.1901

Max Act: 9.1901. Min Act: -0.1700

Data Index: 6397847 (Open Web Text)

Max Activating Token Index: 784

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.1901. Min Range: -10.1901

Max Act: 9.1901. Min Act: -0.1700

Data Index: 3860632 (Open Web Text)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.1901. Min Range: -10.1901

Max Act: 9.1901. Min Act: -0.1700

Data Index: 6934573 (Open Web Text)

Max Activating Token Index: 183

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.1901. Min Range: -10.1901

Max Act: 9.1276. Min Act: -0.1700

Data Index: 1115050 (Open Web Text)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.1901. Min Range: -10.1901

Max Act: 9.0651. Min Act: -0.1700

Data Index: 5047013 (Open Web Text)

Max Activating Token Index: 768

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.1901. Min Range: -10.1901

Max Act: 9.0651. Min Act: -0.1700

Data Index: 8683465 (Open Web Text)

Max Activating Token Index: 1012

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.1901. Min Range: -10.1901

Max Act: 9.0651. Min Act: -0.1700

Data Index: 8468814 (Open Web Text)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.1901. Min Range: -10.1901

Max Act: 9.0026. Min Act: -0.1700

Data Index: 8650357 (Open Web Text)

Max Activating Token Index: 830

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.1901. Min Range: -10.1901

Max Act: 8.9401. Min Act: -0.1700

Data Index: 2542259 (Open Web Text)

Max Activating Token Index: 554

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.1901. Min Range: -10.1901

Max Act: 8.9401. Min Act: -0.1700

Data Index: 952669 (Open Web Text)

Max Activating Token Index: 425

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.1901. Min Range: -10.1901

Max Act: 8.8776. Min Act: -0.1700

Data Index: 5409654 (Open Web Text)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.1901. Min Range: -10.1901

Max Act: 8.8776. Min Act: -0.1700

Data Index: 714612 (Open Web Text)

Max Activating Token Index: 697

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.1901. Min Range: -10.1901

Max Act: 8.8776. Min Act: -0.1697

Data Index: 2799782 (Open Web Text)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #19