< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 65 in Layer 29

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 5.9078. Min Range: -5.9078

Max Act: 5.9078. Min Act: -0.1700

Data Index: 1203901 (Open Web Text)

Max Activating Token Index: 488

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.9078. Min Range: -5.9078

Max Act: 5.6891. Min Act: -0.1700

Data Index: 5410416 (Open Web Text)

Max Activating Token Index: 514

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.9078. Min Range: -5.9078

Max Act: 5.5953. Min Act: -0.1700

Data Index: 5936013 (Open Web Text)

Max Activating Token Index: 954

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.9078. Min Range: -5.9078

Max Act: 5.5016. Min Act: -0.1700

Data Index: 1177494 (Open Web Text)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.9078. Min Range: -5.9078

Max Act: 5.4391. Min Act: -0.1700

Data Index: 335056 (Open Web Text)

Max Activating Token Index: 931

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.9078. Min Range: -5.9078

Max Act: 5.4391. Min Act: -0.1700

Data Index: 3928032 (Open Web Text)

Max Activating Token Index: 475

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.9078. Min Range: -5.9078

Max Act: 5.4391. Min Act: -0.1700

Data Index: 3951664 (Open Web Text)

Max Activating Token Index: 496

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.9078. Min Range: -5.9078

Max Act: 5.3766. Min Act: -0.1700

Data Index: 5870992 (Open Web Text)

Max Activating Token Index: 760

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.9078. Min Range: -5.9078

Max Act: 5.3766. Min Act: -0.1700

Data Index: 5084666 (Open Web Text)

Max Activating Token Index: 590

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.9078. Min Range: -5.9078

Max Act: 5.3766. Min Act: -0.1700

Data Index: 8508829 (Open Web Text)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.9078. Min Range: -5.9078

Max Act: 5.3453. Min Act: -0.1700

Data Index: 5364255 (Open Web Text)

Max Activating Token Index: 623

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.9078. Min Range: -5.9078

Max Act: 5.3141. Min Act: -0.1700

Data Index: 8752288 (Open Web Text)

Max Activating Token Index: 445

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.9078. Min Range: -5.9078

Max Act: 5.3141. Min Act: -0.1700

Data Index: 2803732 (Open Web Text)

Max Activating Token Index: 644

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.9078. Min Range: -5.9078

Max Act: 5.2828. Min Act: -0.1700

Data Index: 2411880 (Open Web Text)

Max Activating Token Index: 181

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.9078. Min Range: -5.9078

Max Act: 5.2828. Min Act: -0.1700

Data Index: 3098396 (Open Web Text)

Max Activating Token Index: 35

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.9078. Min Range: -5.9078

Max Act: 5.2828. Min Act: -0.1700

Data Index: 511840 (Open Web Text)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.9078. Min Range: -5.9078

Max Act: 5.2828. Min Act: -0.1700

Data Index: 1843306 (Open Web Text)

Max Activating Token Index: 494

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.9078. Min Range: -5.9078

Max Act: 5.2516. Min Act: -0.1700

Data Index: 7146792 (Open Web Text)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.9078. Min Range: -5.9078

Max Act: 5.2516. Min Act: -0.1700

Data Index: 3061341 (Open Web Text)

Max Activating Token Index: 227

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.9078. Min Range: -5.9078

Max Act: 5.2516. Min Act: -0.1700

Data Index: 3364788 (Open Web Text)

Max Activating Token Index: 225

Click toggle to see full text

Truncated

Full Text #19