< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 412 in Layer 4

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: 3.2016. Min Range: -3.2016

Max Act: 3.1883. Min Act: -0.1700

Data Index: 2565586 (Open Web Text)

Max Activating Token Index: 874

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 3.2016. Min Range: -3.2016

Max Act: 3.2016. Min Act: -0.1700

Data Index: 5216062 (Open Web Text)

Max Activating Token Index: 909

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 3.2016. Min Range: -3.2016

Max Act: 3.1594. Min Act: -0.1700

Data Index: 1950363 (Open Web Text)

Max Activating Token Index: 837

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 3.2016. Min Range: -3.2016

Max Act: 3.1647. Min Act: -0.1700

Data Index: 8377979 (Open Web Text)

Max Activating Token Index: 916

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 3.2016. Min Range: -3.2016

Max Act: 3.1447. Min Act: -0.1700

Data Index: 3800805 (Open Web Text)

Max Activating Token Index: 965

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 3.2016. Min Range: -3.2016

Max Act: 3.1372. Min Act: -0.1700

Data Index: 8583681 (Open Web Text)

Max Activating Token Index: 766

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 3.2016. Min Range: -3.2016

Max Act: 3.1383. Min Act: -0.1700

Data Index: 2775587 (Open Web Text)

Max Activating Token Index: 818

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 3.2016. Min Range: -3.2016

Max Act: 3.1014. Min Act: -0.1700

Data Index: 6911020 (Open Web Text)

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 3.2016. Min Range: -3.2016

Max Act: 3.1000. Min Act: -0.1700

Data Index: 4953934 (Open Web Text)

Max Activating Token Index: 699

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 3.2016. Min Range: -3.2016

Max Act: 3.0948. Min Act: -0.1700

Data Index: 4962458 (Open Web Text)

Max Activating Token Index: 909

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 3.2016. Min Range: -3.2016

Max Act: 3.0952. Min Act: -0.1700

Data Index: 4953930 (Open Web Text)

Max Activating Token Index: 696

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 3.2016. Min Range: -3.2016

Max Act: 3.0689. Min Act: -0.1700

Data Index: 7132228 (Open Web Text)

Max Activating Token Index: 747

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 3.2016. Min Range: -3.2016

Max Act: 3.0866. Min Act: -0.1700

Data Index: 7325603 (Open Web Text)

Max Activating Token Index: 469

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 3.2016. Min Range: -3.2016

Max Act: 3.0688. Min Act: -0.1700

Data Index: 7421612 (Open Web Text)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 3.2016. Min Range: -3.2016

Max Act: 3.0712. Min Act: -0.1700

Data Index: 7925965 (Open Web Text)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 3.2016. Min Range: -3.2016

Max Act: 3.0821. Min Act: -0.1700

Data Index: 4680834 (Open Web Text)

Max Activating Token Index: 487

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 3.2016. Min Range: -3.2016

Max Act: 3.0609. Min Act: -0.1700

Data Index: 5541066 (Open Web Text)

Max Activating Token Index: 833

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 3.2016. Min Range: -3.2016

Max Act: 3.0603. Min Act: -0.1700

Data Index: 4953932 (Open Web Text)

Max Activating Token Index: 668

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 3.2016. Min Range: -3.2016

Max Act: 3.0731. Min Act: -0.1700

Data Index: 3218255 (Open Web Text)

Max Activating Token Index: 738

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 3.2016. Min Range: -3.2016

Max Act: 3.0638. Min Act: -0.1700

Data Index: 4630529 (Open Web Text)

Max Activating Token Index: 664

Click toggle to see full text

Truncated

Full Text #19