Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 5201 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.9544. Min Act: -0.1697

Data Index: 4452621 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.8919. Min Act: -0.1700

Data Index: 169306 (Open Web Text)

Max Activating Token Index: 287

Text #2

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.8294. Min Act: -0.1700

Data Index: 3033096 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.8294. Min Act: -0.1700

Data Index: 3200866 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.8294. Min Act: -0.1698

Data Index: 3552035 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.8294. Min Act: -0.1700

Data Index: 8316510 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.8294. Min Act: -0.1700

Data Index: 657360 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.8294. Min Act: -0.1700

Data Index: 140414 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7982. Min Act: -0.1700

Data Index: 6693352 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7982. Min Act: -0.1700

Data Index: 8279375 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7669. Min Act: -0.1700

Data Index: 464593 (Open Web Text)

Max Activating Token Index: 1

Text #11

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7669. Min Act: -0.1700

Data Index: 30378 (Open Web Text)

Max Activating Token Index: 1

Text #12

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7669. Min Act: -0.1700

Data Index: 18569 (Open Web Text)

Max Activating Token Index: 1

Text #13

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7669. Min Act: -0.1700

Data Index: 168961 (Open Web Text)

Max Activating Token Index: 1

Text #14

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7669. Min Act: -0.1700

Data Index: 321586 (Open Web Text)

Max Activating Token Index: 1

Text #15

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7669. Min Act: -0.1700

Data Index: 321422 (Open Web Text)

Max Activating Token Index: 1

Text #16

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7669. Min Act: -0.1700

Data Index: 308036 (Open Web Text)

Max Activating Token Index: 1

Text #17

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7669. Min Act: -0.1700

Data Index: 294222 (Open Web Text)

Max Activating Token Index: 1

Text #18

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7669. Min Act: -0.1700

Data Index: 103891 (Open Web Text)

Max Activating Token Index: 1

Text #19

Max Range: 5.9544. Min Range: -5.9544

Max Act: 5.7669. Min Act: -0.1700

Data Index: 268665 (Open Web Text)

Max Activating Token Index: 1