< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 65 in Layer 38

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 12.9998. Min Range: -12.9998

Max Act: 12.9998. Min Act: -0.1700

Data Index: 2847060 (Open Web Text)

Max Activating Token Index: 905

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 12.9998. Min Range: -12.9998

Max Act: 12.8123. Min Act: -0.1700

Data Index: 2970322 (Open Web Text)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 12.9998. Min Range: -12.9998

Max Act: 12.6248. Min Act: -0.1700

Data Index: 7916864 (Open Web Text)

Max Activating Token Index: 804

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 12.9998. Min Range: -12.9998

Max Act: 12.4998. Min Act: -0.1700

Data Index: 7389903 (Open Web Text)

Max Activating Token Index: 781

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 12.9998. Min Range: -12.9998

Max Act: 12.4998. Min Act: -0.1700

Data Index: 6320197 (Open Web Text)

Max Activating Token Index: 793

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 12.9998. Min Range: -12.9998

Max Act: 12.4373. Min Act: -0.1700

Data Index: 7881317 (Open Web Text)

Max Activating Token Index: 302

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 12.9998. Min Range: -12.9998

Max Act: 12.4373. Min Act: -0.1700

Data Index: 3988389 (Open Web Text)

Max Activating Token Index: 768

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 12.9998. Min Range: -12.9998

Max Act: 12.3123. Min Act: -0.1700

Data Index: 3138707 (Open Web Text)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 12.9998. Min Range: -12.9998

Max Act: 12.3748. Min Act: -0.1700

Data Index: 819759 (Open Web Text)

Max Activating Token Index: 814

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 12.9998. Min Range: -12.9998

Max Act: 12.3748. Min Act: -0.1700

Data Index: 980156 (Open Web Text)

Max Activating Token Index: 436

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 12.9998. Min Range: -12.9998

Max Act: 12.3123. Min Act: -0.1700

Data Index: 2139169 (Open Web Text)

Max Activating Token Index: 819

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 12.9998. Min Range: -12.9998

Max Act: 12.1873. Min Act: -0.1700

Data Index: 896696 (Open Web Text)

Max Activating Token Index: 420

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 12.9998. Min Range: -12.9998

Max Act: 12.1873. Min Act: -0.1700

Data Index: 389814 (Open Web Text)

Max Activating Token Index: 551

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 12.9998. Min Range: -12.9998

Max Act: 12.1873. Min Act: -0.1700

Data Index: 5276632 (Open Web Text)

Max Activating Token Index: 424

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 12.9998. Min Range: -12.9998

Max Act: 12.2498. Min Act: -0.1700

Data Index: 4586720 (Open Web Text)

Max Activating Token Index: 893

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 12.9998. Min Range: -12.9998

Max Act: 12.1873. Min Act: -0.1700

Data Index: 5289978 (Open Web Text)

Max Activating Token Index: 775

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 12.9998. Min Range: -12.9998

Max Act: 12.1248. Min Act: -0.1700

Data Index: 5980393 (Open Web Text)

Max Activating Token Index: 599

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 12.9998. Min Range: -12.9998

Max Act: 12.1248. Min Act: -0.1700

Data Index: 4790376 (Open Web Text)

Max Activating Token Index: 37

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 12.9998. Min Range: -12.9998

Max Act: 12.1248. Min Act: -0.1700

Data Index: 7722831 (Open Web Text)

Max Activating Token Index: 849

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 12.9998. Min Range: -12.9998

Max Act: 12.1248. Min Act: -0.1700

Data Index: 3405577 (Open Web Text)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #19