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

Dataset: Open Web Text

Neuron 1127 in Layer 14

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.3390. Min Act: -0.1700

Data Index: 4404207 (Open Web Text)

Max Activating Token Index: 763

Text #1

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.2765. Min Act: -0.1700

Data Index: 2270768 (Open Web Text)

Max Activating Token Index: 417

Text #2

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.2453. Min Act: -0.1700

Data Index: 6820295 (Open Web Text)

Max Activating Token Index: 473

Text #3

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.2453. Min Act: -0.1700

Data Index: 4678716 (Open Web Text)

Max Activating Token Index: 791

Text #4

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.2140. Min Act: -0.1700

Data Index: 1551828 (Open Web Text)

Max Activating Token Index: 368

Text #5

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.2453. Min Act: -0.1700

Data Index: 8283407 (Open Web Text)

Max Activating Token Index: 656

Text #6

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.2140. Min Act: -0.1700

Data Index: 3365884 (Open Web Text)

Max Activating Token Index: 90

Text #7

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.2140. Min Act: -0.1700

Data Index: 842710 (Open Web Text)

Max Activating Token Index: 279

Text #8

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1828. Min Act: -0.1700

Data Index: 1319038 (Open Web Text)

Max Activating Token Index: 400

Text #9

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1828. Min Act: -0.1700

Data Index: 4649519 (Open Web Text)

Max Activating Token Index: 757

Text #10

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1828. Min Act: -0.1700

Data Index: 618673 (Open Web Text)

Max Activating Token Index: 66

Text #11

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1828. Min Act: -0.1700

Data Index: 5071677 (Open Web Text)

Max Activating Token Index: 379

Text #12

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1515. Min Act: -0.1700

Data Index: 6814607 (Open Web Text)

Max Activating Token Index: 103

Text #13

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1828. Min Act: -0.1700

Data Index: 1640054 (Open Web Text)

Max Activating Token Index: 879

Text #14

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1515. Min Act: -0.1700

Data Index: 692269 (Open Web Text)

Max Activating Token Index: 801

Text #15

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1203. Min Act: -0.1700

Data Index: 1019320 (Open Web Text)

Max Activating Token Index: 84

Text #16

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1203. Min Act: -0.1700

Data Index: 2754111 (Open Web Text)

Max Activating Token Index: 291

Text #17

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1203. Min Act: -0.1700

Data Index: 5710271 (Open Web Text)

Max Activating Token Index: 555

Text #18

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1203. Min Act: -0.1700

Data Index: 5549537 (Open Web Text)

Max Activating Token Index: 596

Text #19

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1203. Min Act: -0.1700

Data Index: 5549533 (Open Web Text)

Max Activating Token Index: 324