Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 2982 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.8007. Min Act: -0.1700

Data Index: 905253 (Open Web Text)

Max Activating Token Index: 280

Text #1

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.8320. Min Act: -0.1700

Data Index: 7014992 (Open Web Text)

Max Activating Token Index: 121

Text #2

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.8007. Min Act: -0.1700

Data Index: 7281493 (Open Web Text)

Max Activating Token Index: 747

Text #3

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7695. Min Act: -0.1700

Data Index: 8411196 (Open Web Text)

Max Activating Token Index: 832

Text #4

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7382. Min Act: -0.1700

Data Index: 8130030 (Open Web Text)

Max Activating Token Index: 635

Text #5

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7695. Min Act: -0.1700

Data Index: 1753556 (Open Web Text)

Max Activating Token Index: 44

Text #6

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7382. Min Act: -0.1700

Data Index: 588596 (Open Web Text)

Max Activating Token Index: 374

Text #7

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7382. Min Act: -0.1700

Data Index: 3828350 (Open Web Text)

Max Activating Token Index: 148

Text #8

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7382. Min Act: -0.1700

Data Index: 6475494 (Open Web Text)

Max Activating Token Index: 120

Text #9

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7695. Min Act: -0.1700

Data Index: 6052207 (Open Web Text)

Max Activating Token Index: 123

Text #10

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7382. Min Act: -0.1700

Data Index: 558392 (Open Web Text)

Max Activating Token Index: 220

Text #11

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7382. Min Act: -0.1700

Data Index: 3532743 (Open Web Text)

Max Activating Token Index: 82

Text #12

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7070. Min Act: -0.1700

Data Index: 5021798 (Open Web Text)

Max Activating Token Index: 454

Text #13

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7070. Min Act: -0.1700

Data Index: 3254076 (Open Web Text)

Max Activating Token Index: 314

Text #14

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7382. Min Act: -0.1700

Data Index: 5712912 (Open Web Text)

Max Activating Token Index: 167

Text #15

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7382. Min Act: -0.1700

Data Index: 8167204 (Open Web Text)

Max Activating Token Index: 837

Text #16

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7070. Min Act: -0.1700

Data Index: 5476055 (Open Web Text)

Max Activating Token Index: 825

Text #17

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7070. Min Act: -0.1700

Data Index: 727847 (Open Web Text)

Max Activating Token Index: 550

Text #18

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7070. Min Act: -0.1700

Data Index: 4918017 (Open Web Text)

Max Activating Token Index: 392

Text #19

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7070. Min Act: -0.1700

Data Index: 4675489 (Open Web Text)

Max Activating Token Index: 188