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

Dataset: Open Web Text

Neuron 2722 in Layer 0

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: 3.0584. Min Range: -3.0584

Max Act: 3.0584. Min Act: -0.1700

Data Index: 1105014 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.0584. Min Range: -3.0584

Max Act: 2.9980. Min Act: -0.1700

Data Index: 3370464 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.0584. Min Range: -3.0584

Max Act: 2.9563. Min Act: -0.1700

Data Index: 3278344 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.0584. Min Range: -3.0584

Max Act: 2.9635. Min Act: -0.1700

Data Index: 1328853 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.0584. Min Range: -3.0584

Max Act: 2.9545. Min Act: -0.1700

Data Index: 5182743 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.0584. Min Range: -3.0584

Max Act: 2.9364. Min Act: -0.1700

Data Index: 6696100 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.0584. Min Range: -3.0584

Max Act: 2.9382. Min Act: -0.1700

Data Index: 2792955 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 3.0584. Min Range: -3.0584

Max Act: 2.9363. Min Act: -0.1700

Data Index: 5731293 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.0584. Min Range: -3.0584

Max Act: 2.8978. Min Act: -0.1700

Data Index: 6742523 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 3.0584. Min Range: -3.0584

Max Act: 2.9029. Min Act: -0.1700

Data Index: 1330795 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 3.0584. Min Range: -3.0584

Max Act: 2.9092. Min Act: -0.1700

Data Index: 7690139 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.0584. Min Range: -3.0584

Max Act: 2.8756. Min Act: -0.1700

Data Index: 1049921 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.0584. Min Range: -3.0584

Max Act: 2.8756. Min Act: -0.1700

Data Index: 6615866 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.0584. Min Range: -3.0584

Max Act: 2.8741. Min Act: -0.1700

Data Index: 4991739 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.0584. Min Range: -3.0584

Max Act: 2.8840. Min Act: -0.1700

Data Index: 775399 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.0584. Min Range: -3.0584

Max Act: 2.8770. Min Act: -0.1700

Data Index: 129756 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.0584. Min Range: -3.0584

Max Act: 2.8748. Min Act: -0.1700

Data Index: 482825 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.0584. Min Range: -3.0584

Max Act: 2.8696. Min Act: -0.1700

Data Index: 4278440 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.0584. Min Range: -3.0584

Max Act: 2.8619. Min Act: -0.1700

Data Index: 5492261 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 3.0584. Min Range: -3.0584

Max Act: 2.8588. Min Act: -0.1700

Data Index: 5672919 (Open Web Text)

Max Activating Token Index: 8