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

Dataset: Open Web Text

Neuron 656 in Layer 1

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: 1.1578. Min Range: -1.1578

Max Act: 1.1578. Min Act: -0.1700

Data Index: 2157093 (Open Web Text)

Max Activating Token Index: 867

Text #1

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.1525. Min Act: -0.1700

Data Index: 6082238 (Open Web Text)

Max Activating Token Index: 844

Text #2

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.1332. Min Act: -0.1700

Data Index: 7038435 (Open Web Text)

Max Activating Token Index: 840

Text #3

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.1025. Min Act: -0.1700

Data Index: 2808513 (Open Web Text)

Max Activating Token Index: 862

Text #4

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.0982. Min Act: -0.1700

Data Index: 6516920 (Open Web Text)

Max Activating Token Index: 857

Text #5

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.0962. Min Act: -0.1700

Data Index: 5839241 (Open Web Text)

Max Activating Token Index: 847

Text #6

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.0966. Min Act: -0.1700

Data Index: 4764307 (Open Web Text)

Max Activating Token Index: 857

Text #7

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.0911. Min Act: -0.1700

Data Index: 7790962 (Open Web Text)

Max Activating Token Index: 861

Text #8

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.0934. Min Act: -0.1700

Data Index: 7540460 (Open Web Text)

Max Activating Token Index: 863

Text #9

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.0989. Min Act: -0.1700

Data Index: 7099826 (Open Web Text)

Max Activating Token Index: 844

Text #10

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.0841. Min Act: -0.1700

Data Index: 6543732 (Open Web Text)

Max Activating Token Index: 845

Text #11

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.0829. Min Act: -0.1700

Data Index: 4273938 (Open Web Text)

Max Activating Token Index: 843

Text #12

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.0767. Min Act: -0.1700

Data Index: 1455461 (Open Web Text)

Max Activating Token Index: 868

Text #13

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.0810. Min Act: -0.1700

Data Index: 6062920 (Open Web Text)

Max Activating Token Index: 850

Text #14

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.0854. Min Act: -0.1700

Data Index: 5916617 (Open Web Text)

Max Activating Token Index: 867

Text #15

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.0851. Min Act: -0.1700

Data Index: 1573836 (Open Web Text)

Max Activating Token Index: 859

Text #16

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.0828. Min Act: -0.1700

Data Index: 5491981 (Open Web Text)

Max Activating Token Index: 851

Text #17

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.0834. Min Act: -0.1700

Data Index: 7820644 (Open Web Text)

Max Activating Token Index: 848

Text #18

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.0786. Min Act: -0.1700

Data Index: 8071209 (Open Web Text)

Max Activating Token Index: 850

Text #19

Max Range: 1.1578. Min Range: -1.1578

Max Act: 1.0731. Min Act: -0.1700

Data Index: 1590385 (Open Web Text)

Max Activating Token Index: 846