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

Dataset: Open Web Text

Neuron 1827 in Layer 47

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.3390. Min Range: -8.3390

Max Act: 8.3390. Min Act: -0.1700

Data Index: 3405080 (Open Web Text)

Max Activating Token Index: 266

Text #1

Max Range: 8.3390. Min Range: -8.3390

Max Act: 8.2140. Min Act: -0.1700

Data Index: 271502 (Open Web Text)

Max Activating Token Index: 514

Text #2

Max Range: 8.3390. Min Range: -8.3390

Max Act: 8.1515. Min Act: -0.1700

Data Index: 7160058 (Open Web Text)

Max Activating Token Index: 412

Text #3

Max Range: 8.3390. Min Range: -8.3390

Max Act: 8.0890. Min Act: -0.1700

Data Index: 5157570 (Open Web Text)

Max Activating Token Index: 262

Text #4

Max Range: 8.3390. Min Range: -8.3390

Max Act: 8.0890. Min Act: -0.1700

Data Index: 1737505 (Open Web Text)

Max Activating Token Index: 115

Text #5

Max Range: 8.3390. Min Range: -8.3390

Max Act: 8.1203. Min Act: -0.1700

Data Index: 7284677 (Open Web Text)

Max Activating Token Index: 236

Text #6

Max Range: 8.3390. Min Range: -8.3390

Max Act: 8.0578. Min Act: -0.1700

Data Index: 5216921 (Open Web Text)

Max Activating Token Index: 578

Text #7

Max Range: 8.3390. Min Range: -8.3390

Max Act: 8.0890. Min Act: -0.1700

Data Index: 7420406 (Open Web Text)

Max Activating Token Index: 564

Text #8

Max Range: 8.3390. Min Range: -8.3390

Max Act: 7.9953. Min Act: -0.1700

Data Index: 289609 (Open Web Text)

Max Activating Token Index: 350

Text #9

Max Range: 8.3390. Min Range: -8.3390

Max Act: 7.9640. Min Act: -0.1700

Data Index: 3754710 (Open Web Text)

Max Activating Token Index: 355

Text #10

Max Range: 8.3390. Min Range: -8.3390

Max Act: 7.9953. Min Act: -0.1700

Data Index: 3594272 (Open Web Text)

Max Activating Token Index: 375

Text #11

Max Range: 8.3390. Min Range: -8.3390

Max Act: 7.9328. Min Act: -0.1700

Data Index: 2242987 (Open Web Text)

Max Activating Token Index: 441

Text #12

Max Range: 8.3390. Min Range: -8.3390

Max Act: 7.9640. Min Act: -0.1700

Data Index: 2977108 (Open Web Text)

Max Activating Token Index: 190

Text #13

Max Range: 8.3390. Min Range: -8.3390

Max Act: 7.9953. Min Act: -0.1700

Data Index: 7934252 (Open Web Text)

Max Activating Token Index: 357

Text #14

Max Range: 8.3390. Min Range: -8.3390

Max Act: 7.9015. Min Act: -0.1700

Data Index: 4513522 (Open Web Text)

Max Activating Token Index: 845

Text #15

Max Range: 8.3390. Min Range: -8.3390

Max Act: 7.9328. Min Act: -0.1700

Data Index: 7770123 (Open Web Text)

Max Activating Token Index: 185

Text #16

Max Range: 8.3390. Min Range: -8.3390

Max Act: 7.9015. Min Act: -0.1700

Data Index: 1954272 (Open Web Text)

Max Activating Token Index: 396

Text #17

Max Range: 8.3390. Min Range: -8.3390

Max Act: 7.9640. Min Act: -0.1700

Data Index: 1279174 (Open Web Text)

Max Activating Token Index: 338

Text #18

Max Range: 8.3390. Min Range: -8.3390

Max Act: 7.9328. Min Act: -0.1700

Data Index: 2935754 (Open Web Text)

Max Activating Token Index: 179

Text #19

Max Range: 8.3390. Min Range: -8.3390

Max Act: 7.9328. Min Act: -0.1700

Data Index: 1884854 (Open Web Text)

Max Activating Token Index: 416