< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 643 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.9689. Min Act: -0.1700

Data Index: 968566 (Open Web Text)

Max Activating Token Index: 648

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.9498. Min Act: -0.1700

Data Index: 1753097 (Open Web Text)

Max Activating Token Index: 215

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.9103. Min Act: -0.1700

Data Index: 7673155 (Open Web Text)

Max Activating Token Index: 779

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.9043. Min Act: -0.1700

Data Index: 392555 (Open Web Text)

Max Activating Token Index: 360

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.8817. Min Act: -0.1700

Data Index: 8754325 (Open Web Text)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.8838. Min Act: -0.1700

Data Index: 4986767 (Open Web Text)

Max Activating Token Index: 280

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.8705. Min Act: -0.1700

Data Index: 3791942 (Open Web Text)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.8681. Min Act: -0.1700

Data Index: 8832368 (Open Web Text)

Max Activating Token Index: 435

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.8000. Min Act: -0.1700

Data Index: 7081854 (Open Web Text)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.8113. Min Act: -0.1700

Data Index: 5724885 (Open Web Text)

Max Activating Token Index: 189

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.8080. Min Act: -0.1700

Data Index: 7000653 (Open Web Text)

Max Activating Token Index: 747

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.8199. Min Act: -0.1700

Data Index: 2421606 (Open Web Text)

Max Activating Token Index: 404

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.8054. Min Act: -0.1700

Data Index: 336411 (Open Web Text)

Max Activating Token Index: 107

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.7813. Min Act: -0.1700

Data Index: 4932857 (Open Web Text)

Max Activating Token Index: 137

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.7683. Min Act: -0.1700

Data Index: 7871112 (Open Web Text)

Max Activating Token Index: 794

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.7603. Min Act: -0.1700

Data Index: 3794774 (Open Web Text)

Max Activating Token Index: 142

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.7620. Min Act: -0.1700

Data Index: 3014924 (Open Web Text)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.7534. Min Act: -0.1700

Data Index: 1688021 (Open Web Text)

Max Activating Token Index: 984

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.7502. Min Act: -0.1700

Data Index: 6144243 (Open Web Text)

Max Activating Token Index: 456

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.7427. Min Act: -0.1700

Data Index: 4274600 (Open Web Text)

Max Activating Token Index: 568

Click toggle to see full text

Truncated

Full Text #19