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

Dataset: Open Web Text

Neuron 1617 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: 3.0684. Min Range: -3.0684

Max Act: 3.0523. Min Act: -0.1700

Data Index: 2990158 (Open Web Text)

Max Activating Token Index: 583

Text #1

Max Range: 3.0684. Min Range: -3.0684

Max Act: 3.0684. Min Act: -0.1700

Data Index: 7804904 (Open Web Text)

Max Activating Token Index: 1019

Text #2

Max Range: 3.0684. Min Range: -3.0684

Max Act: 3.0454. Min Act: -0.1700

Data Index: 3207852 (Open Web Text)

Max Activating Token Index: 804

Text #3

Max Range: 3.0684. Min Range: -3.0684

Max Act: 3.0239. Min Act: -0.1700

Data Index: 983260 (Open Web Text)

Max Activating Token Index: 186

Text #4

Max Range: 3.0684. Min Range: -3.0684

Max Act: 3.0348. Min Act: -0.1700

Data Index: 4467373 (Open Web Text)

Max Activating Token Index: 850

Text #5

Max Range: 3.0684. Min Range: -3.0684

Max Act: 3.0232. Min Act: -0.1700

Data Index: 849024 (Open Web Text)

Max Activating Token Index: 658

Text #6

Max Range: 3.0684. Min Range: -3.0684

Max Act: 3.0062. Min Act: -0.1700

Data Index: 6101890 (Open Web Text)

Max Activating Token Index: 655

Text #7

Max Range: 3.0684. Min Range: -3.0684

Max Act: 2.9990. Min Act: -0.1700

Data Index: 5416609 (Open Web Text)

Max Activating Token Index: 515

Text #8

Max Range: 3.0684. Min Range: -3.0684

Max Act: 2.9967. Min Act: -0.1700

Data Index: 4852773 (Open Web Text)

Max Activating Token Index: 17

Text #9

Max Range: 3.0684. Min Range: -3.0684

Max Act: 2.9990. Min Act: -0.1700

Data Index: 360632 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 3.0684. Min Range: -3.0684

Max Act: 2.9609. Min Act: -0.1700

Data Index: 8636350 (Open Web Text)

Max Activating Token Index: 59

Text #11

Max Range: 3.0684. Min Range: -3.0684

Max Act: 2.9677. Min Act: -0.1700

Data Index: 1755888 (Open Web Text)

Max Activating Token Index: 794

Text #12

Max Range: 3.0684. Min Range: -3.0684

Max Act: 2.9715. Min Act: -0.1700

Data Index: 2610182 (Open Web Text)

Max Activating Token Index: 445

Text #13

Max Range: 3.0684. Min Range: -3.0684

Max Act: 2.9591. Min Act: -0.1700

Data Index: 7803667 (Open Web Text)

Max Activating Token Index: 29

Text #14

Max Range: 3.0684. Min Range: -3.0684

Max Act: 2.9450. Min Act: -0.1700

Data Index: 7917485 (Open Web Text)

Max Activating Token Index: 971

Text #15

Max Range: 3.0684. Min Range: -3.0684

Max Act: 2.9639. Min Act: -0.1700

Data Index: 6203422 (Open Web Text)

Max Activating Token Index: 634

Text #16

Max Range: 3.0684. Min Range: -3.0684

Max Act: 2.9699. Min Act: -0.1700

Data Index: 577949 (Open Web Text)

Max Activating Token Index: 370

Text #17

Max Range: 3.0684. Min Range: -3.0684

Max Act: 2.9522. Min Act: -0.1700

Data Index: 2958808 (Open Web Text)

Max Activating Token Index: 334

Text #18

Max Range: 3.0684. Min Range: -3.0684

Max Act: 2.9549. Min Act: -0.1700

Data Index: 5231160 (Open Web Text)

Max Activating Token Index: 659

Text #19

Max Range: 3.0684. Min Range: -3.0684

Max Act: 2.9750. Min Act: -0.1700

Data Index: 4598221 (Open Web Text)

Max Activating Token Index: 417