Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 4089 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')

Text #0

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.8320. Min Act: -0.1700

Data Index: 1729722 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.8063. Min Act: -0.1700

Data Index: 2005963 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.7718. Min Act: -0.1700

Data Index: 5461916 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.7546. Min Act: -0.1699

Data Index: 1542559 (Open Web Text)

Max Activating Token Index: 733

Text #4

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.7546. Min Act: -0.1698

Data Index: 1276378 (Open Web Text)

Max Activating Token Index: 779

Text #5

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.7546. Min Act: -0.1700

Data Index: 3823346 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.7373. Min Act: -0.1700

Data Index: 7039268 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.7373. Min Act: -0.1700

Data Index: 8074357 (Open Web Text)

Max Activating Token Index: 504

Text #8

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.7286. Min Act: -0.1696

Data Index: 2556584 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.7459. Min Act: -0.1700

Data Index: 4271627 (Open Web Text)

Max Activating Token Index: 715

Text #10

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.7373. Min Act: -0.1687

Data Index: 1552675 (Open Web Text)

Max Activating Token Index: 756

Text #11

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.7286. Min Act: -0.1700

Data Index: 4354920 (Open Web Text)

Max Activating Token Index: 984

Text #12

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.7286. Min Act: -0.1700

Data Index: 1940055 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.7200. Min Act: -0.1700

Data Index: 1594881 (Open Web Text)

Max Activating Token Index: 556

Text #14

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.7200. Min Act: -0.1700

Data Index: 1830892 (Open Web Text)

Max Activating Token Index: 60

Text #15

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.7200. Min Act: -0.1700

Data Index: 4917258 (Open Web Text)

Max Activating Token Index: 830

Text #16

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.7113. Min Act: -0.1700

Data Index: 7368497 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.7113. Min Act: -0.1700

Data Index: 338632 (Open Web Text)

Max Activating Token Index: 819

Text #18

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.7113. Min Act: -0.1699

Data Index: 6762969 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.7027. Min Act: -0.1700

Data Index: 1105941 (Open Web Text)

Max Activating Token Index: 672