Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 3704 in Layer 14

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1016. Min Range: -5.1016

Max Act: 5.1016. Min Act: -0.1700

Data Index: 7521947 (Open Web Text)

Max Activating Token Index: 338

Text #1

Max Range: 5.1016. Min Range: -5.1016

Max Act: 5.0704. Min Act: -0.1700

Data Index: 254014 (Open Web Text)

Max Activating Token Index: 360

Text #2

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.8829. Min Act: -0.1700

Data Index: 819199 (Open Web Text)

Max Activating Token Index: 548

Text #3

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.9141. Min Act: -0.1700

Data Index: 5723775 (Open Web Text)

Max Activating Token Index: 917

Text #4

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.8829. Min Act: -0.1700

Data Index: 355282 (Open Web Text)

Max Activating Token Index: 914

Text #5

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.8516. Min Act: -0.1700

Data Index: 224330 (Open Web Text)

Max Activating Token Index: 187

Text #6

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.8204. Min Act: -0.1700

Data Index: 3584970 (Open Web Text)

Max Activating Token Index: 828

Text #7

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.8516. Min Act: -0.1700

Data Index: 2785347 (Open Web Text)

Max Activating Token Index: 683

Text #8

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.8516. Min Act: -0.1700

Data Index: 4704893 (Open Web Text)

Max Activating Token Index: 855

Text #9

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.8204. Min Act: -0.1700

Data Index: 3844746 (Open Web Text)

Max Activating Token Index: 521

Text #10

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.7891. Min Act: -0.1700

Data Index: 953666 (Open Web Text)

Max Activating Token Index: 887

Text #11

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.7891. Min Act: -0.1700

Data Index: 6930820 (Open Web Text)

Max Activating Token Index: 230

Text #12

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.7891. Min Act: -0.1700

Data Index: 2976899 (Open Web Text)

Max Activating Token Index: 24

Text #13

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.7891. Min Act: -0.1700

Data Index: 6578398 (Open Web Text)

Max Activating Token Index: 200

Text #14

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.7891. Min Act: -0.1700

Data Index: 718513 (Open Web Text)

Max Activating Token Index: 445

Text #15

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.7891. Min Act: -0.1700

Data Index: 2203313 (Open Web Text)

Max Activating Token Index: 314

Text #16

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.7891. Min Act: -0.1700

Data Index: 4561989 (Open Web Text)

Max Activating Token Index: 163

Text #17

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.7266. Min Act: -0.1700

Data Index: 4695528 (Open Web Text)

Max Activating Token Index: 320

Text #18

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.7891. Min Act: -0.1700

Data Index: 4309598 (Open Web Text)

Max Activating Token Index: 249

Text #19

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.7266. Min Act: -0.1700

Data Index: 3976437 (Open Web Text)

Max Activating Token Index: 629