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

Dataset: Open Web Text

Neuron 2448 in Layer 17

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1016. Min Range: -4.1016

Max Act: 4.1016. Min Act: -0.1700

Data Index: 3659373 (Open Web Text)

Max Activating Token Index: 547

Text #1

Max Range: 4.1016. Min Range: -4.1016

Max Act: 4.1016. Min Act: -0.1700

Data Index: 6865772 (Open Web Text)

Max Activating Token Index: 975

Text #2

Max Range: 4.1016. Min Range: -4.1016

Max Act: 4.0391. Min Act: -0.1700

Data Index: 4246477 (Open Web Text)

Max Activating Token Index: 804

Text #3

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.9766. Min Act: -0.1700

Data Index: 6697881 (Open Web Text)

Max Activating Token Index: 1017

Text #4

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.9766. Min Act: -0.1700

Data Index: 3281857 (Open Web Text)

Max Activating Token Index: 850

Text #5

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.9766. Min Act: -0.1700

Data Index: 7492867 (Open Web Text)

Max Activating Token Index: 221

Text #6

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.9453. Min Act: -0.1700

Data Index: 5860425 (Open Web Text)

Max Activating Token Index: 512

Text #7

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.9453. Min Act: -0.1700

Data Index: 5951188 (Open Web Text)

Max Activating Token Index: 141

Text #8

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.9766. Min Act: -0.1700

Data Index: 3899075 (Open Web Text)

Max Activating Token Index: 890

Text #9

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.9453. Min Act: -0.1700

Data Index: 8625565 (Open Web Text)

Max Activating Token Index: 764

Text #10

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.9453. Min Act: -0.1700

Data Index: 7551667 (Open Web Text)

Max Activating Token Index: 478

Text #11

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.9453. Min Act: -0.1700

Data Index: 4750016 (Open Web Text)

Max Activating Token Index: 507

Text #12

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.9453. Min Act: -0.1700

Data Index: 2149714 (Open Web Text)

Max Activating Token Index: 998

Text #13

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.9453. Min Act: -0.1700

Data Index: 1820004 (Open Web Text)

Max Activating Token Index: 192

Text #14

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.9453. Min Act: -0.1700

Data Index: 923168 (Open Web Text)

Max Activating Token Index: 701

Text #15

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.9141. Min Act: -0.1700

Data Index: 1958710 (Open Web Text)

Max Activating Token Index: 453

Text #16

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.8828. Min Act: -0.1700

Data Index: 5548501 (Open Web Text)

Max Activating Token Index: 512

Text #17

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.9141. Min Act: -0.1700

Data Index: 639911 (Open Web Text)

Max Activating Token Index: 525

Text #18

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.9141. Min Act: -0.1700

Data Index: 249410 (Open Web Text)

Max Activating Token Index: 1020

Text #19

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.8828. Min Act: -0.1700

Data Index: 2973623 (Open Web Text)

Max Activating Token Index: 91