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

Dataset: Open Web Text

Neuron 1474 in Layer 3

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: 3.0720. Min Range: -3.0720

Max Act: 3.0720. Min Act: -0.1700

Data Index: 7717166 (Open Web Text)

Max Activating Token Index: 660

Text #1

Max Range: 3.0720. Min Range: -3.0720

Max Act: 3.0300. Min Act: -0.1700

Data Index: 694427 (Open Web Text)

Max Activating Token Index: 77

Text #2

Max Range: 3.0720. Min Range: -3.0720

Max Act: 2.9896. Min Act: -0.1700

Data Index: 6243878 (Open Web Text)

Max Activating Token Index: 833

Text #3

Max Range: 3.0720. Min Range: -3.0720

Max Act: 3.0047. Min Act: -0.1700

Data Index: 3175966 (Open Web Text)

Max Activating Token Index: 860

Text #4

Max Range: 3.0720. Min Range: -3.0720

Max Act: 2.9725. Min Act: -0.1700

Data Index: 5285181 (Open Web Text)

Max Activating Token Index: 522

Text #5

Max Range: 3.0720. Min Range: -3.0720

Max Act: 2.9564. Min Act: -0.1700

Data Index: 45629 (Open Web Text)

Max Activating Token Index: 1001

Text #6

Max Range: 3.0720. Min Range: -3.0720

Max Act: 2.9724. Min Act: -0.1700

Data Index: 1701243 (Open Web Text)

Max Activating Token Index: 639

Text #7

Max Range: 3.0720. Min Range: -3.0720

Max Act: 2.9941. Min Act: -0.1700

Data Index: 2877075 (Open Web Text)

Max Activating Token Index: 867

Text #8

Max Range: 3.0720. Min Range: -3.0720

Max Act: 2.9822. Min Act: -0.1700

Data Index: 4322889 (Open Web Text)

Max Activating Token Index: 171

Text #9

Max Range: 3.0720. Min Range: -3.0720

Max Act: 2.9664. Min Act: -0.1700

Data Index: 6982761 (Open Web Text)

Max Activating Token Index: 132

Text #10

Max Range: 3.0720. Min Range: -3.0720

Max Act: 2.9583. Min Act: -0.1700

Data Index: 1799416 (Open Web Text)

Max Activating Token Index: 269

Text #11

Max Range: 3.0720. Min Range: -3.0720

Max Act: 2.9572. Min Act: -0.1700

Data Index: 292313 (Open Web Text)

Max Activating Token Index: 92

Text #12

Max Range: 3.0720. Min Range: -3.0720

Max Act: 2.9341. Min Act: -0.1700

Data Index: 3947712 (Open Web Text)

Max Activating Token Index: 863

Text #13

Max Range: 3.0720. Min Range: -3.0720

Max Act: 2.9339. Min Act: -0.1700

Data Index: 1101974 (Open Web Text)

Max Activating Token Index: 1022

Text #14

Max Range: 3.0720. Min Range: -3.0720

Max Act: 2.9236. Min Act: -0.1700

Data Index: 6908204 (Open Web Text)

Max Activating Token Index: 966

Text #15

Max Range: 3.0720. Min Range: -3.0720

Max Act: 2.9113. Min Act: -0.1700

Data Index: 5047254 (Open Web Text)

Max Activating Token Index: 518

Text #16

Max Range: 3.0720. Min Range: -3.0720

Max Act: 2.9198. Min Act: -0.1700

Data Index: 152484 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 3.0720. Min Range: -3.0720

Max Act: 2.9194. Min Act: -0.1700

Data Index: 288331 (Open Web Text)

Max Activating Token Index: 190

Text #18

Max Range: 3.0720. Min Range: -3.0720

Max Act: 2.9741. Min Act: -0.1700

Data Index: 2877087 (Open Web Text)

Max Activating Token Index: 790

Text #19

Max Range: 3.0720. Min Range: -3.0720

Max Act: 2.9236. Min Act: -0.1700

Data Index: 1556683 (Open Web Text)

Max Activating Token Index: 1013