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

Dataset: Open Web Text

Neuron 1520 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: 0.9486. Min Range: -0.9486

Max Act: 0.9486. Min Act: -0.1700

Data Index: 7808867 (Open Web Text)

Max Activating Token Index: 693

Text #1

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.9056. Min Act: -0.1700

Data Index: 3780239 (Open Web Text)

Max Activating Token Index: 653

Text #2

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.9013. Min Act: -0.1700

Data Index: 1992421 (Open Web Text)

Max Activating Token Index: 748

Text #3

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8884. Min Act: -0.1700

Data Index: 8417517 (Open Web Text)

Max Activating Token Index: 632

Text #4

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8909. Min Act: -0.1700

Data Index: 7819749 (Open Web Text)

Max Activating Token Index: 550

Text #5

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.9007. Min Act: -0.1700

Data Index: 1767811 (Open Web Text)

Max Activating Token Index: 610

Text #6

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.9105. Min Act: -0.1700

Data Index: 2923373 (Open Web Text)

Max Activating Token Index: 601

Text #7

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8909. Min Act: -0.1700

Data Index: 5424910 (Open Web Text)

Max Activating Token Index: 622

Text #8

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8864. Min Act: -0.1700

Data Index: 7562220 (Open Web Text)

Max Activating Token Index: 637

Text #9

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8565. Min Act: -0.1700

Data Index: 3043041 (Open Web Text)

Max Activating Token Index: 593

Text #10

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8778. Min Act: -0.1700

Data Index: 1595433 (Open Web Text)

Max Activating Token Index: 648

Text #11

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8651. Min Act: -0.1700

Data Index: 1597068 (Open Web Text)

Max Activating Token Index: 577

Text #12

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8723. Min Act: -0.1700

Data Index: 1419378 (Open Web Text)

Max Activating Token Index: 622

Text #13

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8607. Min Act: -0.1700

Data Index: 5335974 (Open Web Text)

Max Activating Token Index: 474

Text #14

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8632. Min Act: -0.1700

Data Index: 2070841 (Open Web Text)

Max Activating Token Index: 645

Text #15

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8427. Min Act: -0.1700

Data Index: 6393891 (Open Web Text)

Max Activating Token Index: 772

Text #16

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8398. Min Act: -0.1700

Data Index: 6431812 (Open Web Text)

Max Activating Token Index: 649

Text #17

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8531. Min Act: -0.1700

Data Index: 6726839 (Open Web Text)

Max Activating Token Index: 650

Text #18

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8497. Min Act: -0.1700

Data Index: 7157985 (Open Web Text)

Max Activating Token Index: 584

Text #19

Max Range: 0.9486. Min Range: -0.9486

Max Act: 0.8465. Min Act: -0.1700

Data Index: 2164326 (Open Web Text)

Max Activating Token Index: 706