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

Dataset: Open Web Text

Neuron 5807 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0356

Data Index: 237 (Open Web Text)

Max Activating Token Index: 699

Text #1

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0572

Data Index: 2458 (Open Web Text)

Max Activating Token Index: 184

Text #2

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0700

Data Index: 321 (Open Web Text)

Max Activating Token Index: 1009

Text #3

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0453

Data Index: 1205 (Open Web Text)

Max Activating Token Index: 725

Text #4

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0401

Data Index: 2368 (Open Web Text)

Max Activating Token Index: 91

Text #5

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0340

Data Index: 367 (Open Web Text)

Max Activating Token Index: 986

Text #6

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0903

Data Index: 2143 (Open Web Text)

Max Activating Token Index: 591

Text #7

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0380

Data Index: 322 (Open Web Text)

Max Activating Token Index: 136

Text #8

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0281

Data Index: 1939 (Open Web Text)

Max Activating Token Index: 531

Text #9

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0253

Data Index: 1552 (Open Web Text)

Max Activating Token Index: 674

Text #10

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0429

Data Index: 368 (Open Web Text)

Max Activating Token Index: 190

Text #11

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0619

Data Index: 1911 (Open Web Text)

Max Activating Token Index: 102

Text #12

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0440

Data Index: 1443 (Open Web Text)

Max Activating Token Index: 1014

Text #13

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0354

Data Index: 1750 (Open Web Text)

Max Activating Token Index: 492

Text #14

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0337

Data Index: 1245 (Open Web Text)

Max Activating Token Index: 1014

Text #15

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0480

Data Index: 860 (Open Web Text)

Max Activating Token Index: 126

Text #16

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0656

Data Index: 736 (Open Web Text)

Max Activating Token Index: 588

Text #17

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0285

Data Index: 1208 (Open Web Text)

Max Activating Token Index: 675

Text #18

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0443

Data Index: 1720 (Open Web Text)

Max Activating Token Index: 638

Text #19

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0426

Data Index: 388 (Open Web Text)

Max Activating Token Index: 633