Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1484 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.8642. Min Range: -3.8642

Max Act: 3.8642. Min Act: -0.1700

Data Index: 6337412 (Open Web Text)

Max Activating Token Index: 644

Text #1

Max Range: 3.8642. Min Range: -3.8642

Max Act: 3.8513. Min Act: -0.1700

Data Index: 1250959 (Open Web Text)

Max Activating Token Index: 861

Text #2

Max Range: 3.8642. Min Range: -3.8642

Max Act: 3.7571. Min Act: -0.1700

Data Index: 1683358 (Open Web Text)

Max Activating Token Index: 257

Text #3

Max Range: 3.8642. Min Range: -3.8642

Max Act: 3.7065. Min Act: -0.1700

Data Index: 992469 (Open Web Text)

Max Activating Token Index: 780

Text #4

Max Range: 3.8642. Min Range: -3.8642

Max Act: 3.6947. Min Act: -0.1700

Data Index: 1737203 (Open Web Text)

Max Activating Token Index: 49

Text #5

Max Range: 3.8642. Min Range: -3.8642

Max Act: 3.6603. Min Act: -0.1700

Data Index: 738368 (Open Web Text)

Max Activating Token Index: 104

Text #6

Max Range: 3.8642. Min Range: -3.8642

Max Act: 3.6519. Min Act: -0.1700

Data Index: 1650382 (Open Web Text)

Max Activating Token Index: 485

Text #7

Max Range: 3.8642. Min Range: -3.8642

Max Act: 3.5716. Min Act: -0.1700

Data Index: 3134874 (Open Web Text)

Max Activating Token Index: 962

Text #8

Max Range: 3.8642. Min Range: -3.8642

Max Act: 3.5823. Min Act: -0.1700

Data Index: 6362983 (Open Web Text)

Max Activating Token Index: 37

Text #9

Max Range: 3.8642. Min Range: -3.8642

Max Act: 3.6016. Min Act: -0.1700

Data Index: 2484256 (Open Web Text)

Max Activating Token Index: 298

Text #10

Max Range: 3.8642. Min Range: -3.8642

Max Act: 3.5828. Min Act: -0.1700

Data Index: 4475946 (Open Web Text)

Max Activating Token Index: 869

Text #11

Max Range: 3.8642. Min Range: -3.8642

Max Act: 3.5651. Min Act: -0.1700

Data Index: 5019694 (Open Web Text)

Max Activating Token Index: 70

Text #12

Max Range: 3.8642. Min Range: -3.8642

Max Act: 3.5544. Min Act: -0.1700

Data Index: 6599716 (Open Web Text)

Max Activating Token Index: 272

Text #13

Max Range: 3.8642. Min Range: -3.8642

Max Act: 3.5376. Min Act: -0.1700

Data Index: 5991412 (Open Web Text)

Max Activating Token Index: 838

Text #14

Max Range: 3.8642. Min Range: -3.8642

Max Act: 3.5419. Min Act: -0.1700

Data Index: 1957409 (Open Web Text)

Max Activating Token Index: 994

Text #15

Max Range: 3.8642. Min Range: -3.8642

Max Act: 3.5358. Min Act: -0.1700

Data Index: 3740318 (Open Web Text)

Max Activating Token Index: 79

Text #16

Max Range: 3.8642. Min Range: -3.8642

Max Act: 3.5014. Min Act: -0.1700

Data Index: 3709652 (Open Web Text)

Max Activating Token Index: 961

Text #17

Max Range: 3.8642. Min Range: -3.8642

Max Act: 3.4929. Min Act: -0.1700

Data Index: 4204584 (Open Web Text)

Max Activating Token Index: 592

Text #18

Max Range: 3.8642. Min Range: -3.8642

Max Act: 3.5043. Min Act: -0.1700

Data Index: 6270516 (Open Web Text)

Max Activating Token Index: 466

Text #19

Max Range: 3.8642. Min Range: -3.8642

Max Act: 3.4740. Min Act: -0.1700

Data Index: 6711824 (Open Web Text)

Max Activating Token Index: 616