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

Dataset: Open Web Text

Neuron 4581 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: 7.6379. Min Range: -7.6379

Max Act: 7.6379. Min Act: -0.1700

Data Index: 1386309 (Open Web Text)

Max Activating Token Index: 228

Text #1

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.3879. Min Act: -0.1700

Data Index: 1823187 (Open Web Text)

Max Activating Token Index: 734

Text #2

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.2629. Min Act: -0.1700

Data Index: 8042630 (Open Web Text)

Max Activating Token Index: 480

Text #3

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.2004. Min Act: -0.1700

Data Index: 255954 (Open Web Text)

Max Activating Token Index: 341

Text #4

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.1379. Min Act: -0.1700

Data Index: 4742712 (Open Web Text)

Max Activating Token Index: 917

Text #5

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.1067. Min Act: -0.1700

Data Index: 7862890 (Open Web Text)

Max Activating Token Index: 804

Text #6

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.1067. Min Act: -0.1700

Data Index: 2768819 (Open Web Text)

Max Activating Token Index: 341

Text #7

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.0754. Min Act: -0.1700

Data Index: 2219730 (Open Web Text)

Max Activating Token Index: 916

Text #8

Max Range: 7.6379. Min Range: -7.6379

Max Act: 6.9817. Min Act: -0.1700

Data Index: 4802893 (Open Web Text)

Max Activating Token Index: 715

Text #9

Max Range: 7.6379. Min Range: -7.6379

Max Act: 6.9192. Min Act: -0.1700

Data Index: 5317344 (Open Web Text)

Max Activating Token Index: 262

Text #10

Max Range: 7.6379. Min Range: -7.6379

Max Act: 6.8879. Min Act: -0.1700

Data Index: 2428440 (Open Web Text)

Max Activating Token Index: 672

Text #11

Max Range: 7.6379. Min Range: -7.6379

Max Act: 6.8879. Min Act: -0.1700

Data Index: 4259527 (Open Web Text)

Max Activating Token Index: 527

Text #12

Max Range: 7.6379. Min Range: -7.6379

Max Act: 6.8567. Min Act: -0.1700

Data Index: 5499758 (Open Web Text)

Max Activating Token Index: 843

Text #13

Max Range: 7.6379. Min Range: -7.6379

Max Act: 6.8254. Min Act: -0.1700

Data Index: 268395 (Open Web Text)

Max Activating Token Index: 512

Text #14

Max Range: 7.6379. Min Range: -7.6379

Max Act: 6.8254. Min Act: -0.1700

Data Index: 5031867 (Open Web Text)

Max Activating Token Index: 888

Text #15

Max Range: 7.6379. Min Range: -7.6379

Max Act: 6.8254. Min Act: -0.1700

Data Index: 5001473 (Open Web Text)

Max Activating Token Index: 53

Text #16

Max Range: 7.6379. Min Range: -7.6379

Max Act: 6.8254. Min Act: -0.1700

Data Index: 6566413 (Open Web Text)

Max Activating Token Index: 182

Text #17

Max Range: 7.6379. Min Range: -7.6379

Max Act: 6.8254. Min Act: -0.1700

Data Index: 7869363 (Open Web Text)

Max Activating Token Index: 297

Text #18

Max Range: 7.6379. Min Range: -7.6379

Max Act: 6.7942. Min Act: -0.1700

Data Index: 30368 (Open Web Text)

Max Activating Token Index: 502

Text #19

Max Range: 7.6379. Min Range: -7.6379

Max Act: 6.7942. Min Act: -0.1700

Data Index: 6769525 (Open Web Text)

Max Activating Token Index: 707