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

Dataset: Open Web Text

Neuron 1262 in Layer 19

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.3390. Min Act: -0.1700

Data Index: 4430865 (Open Web Text)

Max Activating Token Index: 694

Text #1

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.9953. Min Act: -0.1700

Data Index: 824323 (Open Web Text)

Max Activating Token Index: 460

Text #2

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.9640. Min Act: -0.1700

Data Index: 4349045 (Open Web Text)

Max Activating Token Index: 250

Text #3

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.9328. Min Act: -0.1700

Data Index: 824330 (Open Web Text)

Max Activating Token Index: 584

Text #4

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.9015. Min Act: -0.1700

Data Index: 997995 (Open Web Text)

Max Activating Token Index: 338

Text #5

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.6828. Min Act: -0.1700

Data Index: 6090847 (Open Web Text)

Max Activating Token Index: 307

Text #6

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.6515. Min Act: -0.1700

Data Index: 8060279 (Open Web Text)

Max Activating Token Index: 536

Text #7

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.5890. Min Act: -0.1700

Data Index: 3008008 (Open Web Text)

Max Activating Token Index: 921

Text #8

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.5890. Min Act: -0.1700

Data Index: 2997861 (Open Web Text)

Max Activating Token Index: 968

Text #9

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.5578. Min Act: -0.1700

Data Index: 2409606 (Open Web Text)

Max Activating Token Index: 822

Text #10

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.5890. Min Act: -0.1700

Data Index: 4356046 (Open Web Text)

Max Activating Token Index: 544

Text #11

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.6203. Min Act: -0.1700

Data Index: 4793888 (Open Web Text)

Max Activating Token Index: 970

Text #12

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.5578. Min Act: -0.1700

Data Index: 4658100 (Open Web Text)

Max Activating Token Index: 465

Text #13

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.5578. Min Act: -0.1700

Data Index: 8787594 (Open Web Text)

Max Activating Token Index: 184

Text #14

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.5890. Min Act: -0.1700

Data Index: 107748 (Open Web Text)

Max Activating Token Index: 272

Text #15

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.5578. Min Act: -0.1700

Data Index: 1910771 (Open Web Text)

Max Activating Token Index: 177

Text #16

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.5265. Min Act: -0.1700

Data Index: 3597080 (Open Web Text)

Max Activating Token Index: 651

Text #17

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.5265. Min Act: -0.1700

Data Index: 1170246 (Open Web Text)

Max Activating Token Index: 204

Text #18

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.5265. Min Act: -0.1700

Data Index: 4463112 (Open Web Text)

Max Activating Token Index: 126

Text #19

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.5578. Min Act: -0.1700

Data Index: 1971871 (Open Web Text)

Max Activating Token Index: 650