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

Dataset: Open Web Text

Neuron 2052 in Layer 5

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: 4.7587. Min Range: -4.7587

Max Act: 4.7332. Min Act: -0.1700

Data Index: 5768870 (Open Web Text)

Max Activating Token Index: 629

Text #1

Max Range: 4.7587. Min Range: -4.7587

Max Act: 4.7575. Min Act: -0.1700

Data Index: 2446978 (Open Web Text)

Max Activating Token Index: 41

Text #2

Max Range: 4.7587. Min Range: -4.7587

Max Act: 4.7587. Min Act: -0.1700

Data Index: 4813072 (Open Web Text)

Max Activating Token Index: 271

Text #3

Max Range: 4.7587. Min Range: -4.7587

Max Act: 4.6676. Min Act: -0.1700

Data Index: 7285617 (Open Web Text)

Max Activating Token Index: 577

Text #4

Max Range: 4.7587. Min Range: -4.7587

Max Act: 4.6880. Min Act: -0.1700

Data Index: 4474325 (Open Web Text)

Max Activating Token Index: 778

Text #5

Max Range: 4.7587. Min Range: -4.7587

Max Act: 4.6629. Min Act: -0.1700

Data Index: 6491684 (Open Web Text)

Max Activating Token Index: 818

Text #6

Max Range: 4.7587. Min Range: -4.7587

Max Act: 4.6267. Min Act: -0.1700

Data Index: 6962338 (Open Web Text)

Max Activating Token Index: 212

Text #7

Max Range: 4.7587. Min Range: -4.7587

Max Act: 4.6382. Min Act: -0.1700

Data Index: 3321456 (Open Web Text)

Max Activating Token Index: 824

Text #8

Max Range: 4.7587. Min Range: -4.7587

Max Act: 4.6148. Min Act: -0.1700

Data Index: 7536728 (Open Web Text)

Max Activating Token Index: 675

Text #9

Max Range: 4.7587. Min Range: -4.7587

Max Act: 4.6188. Min Act: -0.1700

Data Index: 7952404 (Open Web Text)

Max Activating Token Index: 301

Text #10

Max Range: 4.7587. Min Range: -4.7587

Max Act: 4.6121. Min Act: -0.1700

Data Index: 197373 (Open Web Text)

Max Activating Token Index: 408

Text #11

Max Range: 4.7587. Min Range: -4.7587

Max Act: 4.5974. Min Act: -0.1700

Data Index: 2168461 (Open Web Text)

Max Activating Token Index: 327

Text #12

Max Range: 4.7587. Min Range: -4.7587

Max Act: 4.5794. Min Act: -0.1700

Data Index: 5858280 (Open Web Text)

Max Activating Token Index: 430

Text #13

Max Range: 4.7587. Min Range: -4.7587

Max Act: 4.6091. Min Act: -0.1700

Data Index: 4890728 (Open Web Text)

Max Activating Token Index: 315

Text #14

Max Range: 4.7587. Min Range: -4.7587

Max Act: 4.5801. Min Act: -0.1700

Data Index: 3975203 (Open Web Text)

Max Activating Token Index: 649

Text #15

Max Range: 4.7587. Min Range: -4.7587

Max Act: 4.5794. Min Act: -0.1700

Data Index: 5017678 (Open Web Text)

Max Activating Token Index: 722

Text #16

Max Range: 4.7587. Min Range: -4.7587

Max Act: 4.5792. Min Act: -0.1700

Data Index: 4263167 (Open Web Text)

Max Activating Token Index: 99

Text #17

Max Range: 4.7587. Min Range: -4.7587

Max Act: 4.6007. Min Act: -0.1700

Data Index: 5522609 (Open Web Text)

Max Activating Token Index: 500

Text #18

Max Range: 4.7587. Min Range: -4.7587

Max Act: 4.5984. Min Act: -0.1700

Data Index: 1883808 (Open Web Text)

Max Activating Token Index: 723

Text #19

Max Range: 4.7587. Min Range: -4.7587

Max Act: 4.5919. Min Act: -0.1700

Data Index: 1674351 (Open Web Text)

Max Activating Token Index: 495