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

Dataset: Open Web Text

Neuron 3755 in Layer 16

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: 4.8320. Min Act: -0.1700

Data Index: 3049168 (Open Web Text)

Max Activating Token Index: 913

Text #1

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.8008. Min Act: -0.1700

Data Index: 8484061 (Open Web Text)

Max Activating Token Index: 582

Text #2

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6445. Min Act: -0.1700

Data Index: 7600426 (Open Web Text)

Max Activating Token Index: 857

Text #3

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.6133. Min Act: -0.1700

Data Index: 3775872 (Open Web Text)

Max Activating Token Index: 77

Text #4

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5195. Min Act: -0.1700

Data Index: 1621427 (Open Web Text)

Max Activating Token Index: 54

Text #5

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5195. Min Act: -0.1700

Data Index: 5674977 (Open Web Text)

Max Activating Token Index: 648

Text #6

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4883. Min Act: -0.1700

Data Index: 1108346 (Open Web Text)

Max Activating Token Index: 937

Text #7

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4883. Min Act: -0.1700

Data Index: 8791342 (Open Web Text)

Max Activating Token Index: 473

Text #8

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4883. Min Act: -0.1700

Data Index: 4590082 (Open Web Text)

Max Activating Token Index: 312

Text #9

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.5195. Min Act: -0.1700

Data Index: 7143759 (Open Web Text)

Max Activating Token Index: 65

Text #10

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4883. Min Act: -0.1700

Data Index: 7922214 (Open Web Text)

Max Activating Token Index: 198

Text #11

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4570. Min Act: -0.1700

Data Index: 7492387 (Open Web Text)

Max Activating Token Index: 982

Text #12

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4570. Min Act: -0.1700

Data Index: 6891686 (Open Web Text)

Max Activating Token Index: 872

Text #13

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4570. Min Act: -0.1700

Data Index: 4998780 (Open Web Text)

Max Activating Token Index: 27

Text #14

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4258. Min Act: -0.1700

Data Index: 5143168 (Open Web Text)

Max Activating Token Index: 997

Text #15

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4258. Min Act: -0.1700

Data Index: 4525493 (Open Web Text)

Max Activating Token Index: 117

Text #16

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4258. Min Act: -0.1700

Data Index: 7031377 (Open Web Text)

Max Activating Token Index: 321

Text #17

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4570. Min Act: -0.1700

Data Index: 737385 (Open Web Text)

Max Activating Token Index: 469

Text #18

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4258. Min Act: -0.1700

Data Index: 7574546 (Open Web Text)

Max Activating Token Index: 778

Text #19

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.4258. Min Act: -0.1700

Data Index: 1713644 (Open Web Text)

Max Activating Token Index: 361