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

Dataset: Open Web Text

Neuron 1225 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: 3.0854. Min Range: -3.0854

Max Act: 3.0854. Min Act: -0.1700

Data Index: 8529300 (Open Web Text)

Max Activating Token Index: 446

Text #1

Max Range: 3.0854. Min Range: -3.0854

Max Act: 3.0741. Min Act: -0.1700

Data Index: 6952865 (Open Web Text)

Max Activating Token Index: 569

Text #2

Max Range: 3.0854. Min Range: -3.0854

Max Act: 3.0490. Min Act: -0.1700

Data Index: 7669658 (Open Web Text)

Max Activating Token Index: 52

Text #3

Max Range: 3.0854. Min Range: -3.0854

Max Act: 3.0276. Min Act: -0.1700

Data Index: 5517547 (Open Web Text)

Max Activating Token Index: 474

Text #4

Max Range: 3.0854. Min Range: -3.0854

Max Act: 3.0238. Min Act: -0.1700

Data Index: 617166 (Open Web Text)

Max Activating Token Index: 543

Text #5

Max Range: 3.0854. Min Range: -3.0854

Max Act: 2.9848. Min Act: -0.1700

Data Index: 8119442 (Open Web Text)

Max Activating Token Index: 264

Text #6

Max Range: 3.0854. Min Range: -3.0854

Max Act: 2.9695. Min Act: -0.1700

Data Index: 3971238 (Open Web Text)

Max Activating Token Index: 781

Text #7

Max Range: 3.0854. Min Range: -3.0854

Max Act: 2.9812. Min Act: -0.1700

Data Index: 2689481 (Open Web Text)

Max Activating Token Index: 274

Text #8

Max Range: 3.0854. Min Range: -3.0854

Max Act: 2.9571. Min Act: -0.1700

Data Index: 8601794 (Open Web Text)

Max Activating Token Index: 133

Text #9

Max Range: 3.0854. Min Range: -3.0854

Max Act: 2.9353. Min Act: -0.1700

Data Index: 1482986 (Open Web Text)

Max Activating Token Index: 482

Text #10

Max Range: 3.0854. Min Range: -3.0854

Max Act: 2.9208. Min Act: -0.1700

Data Index: 4246456 (Open Web Text)

Max Activating Token Index: 572

Text #11

Max Range: 3.0854. Min Range: -3.0854

Max Act: 2.9043. Min Act: -0.1700

Data Index: 6690280 (Open Web Text)

Max Activating Token Index: 591

Text #12

Max Range: 3.0854. Min Range: -3.0854

Max Act: 2.8994. Min Act: -0.1700

Data Index: 1442668 (Open Web Text)

Max Activating Token Index: 487

Text #13

Max Range: 3.0854. Min Range: -3.0854

Max Act: 2.9168. Min Act: -0.1700

Data Index: 4224014 (Open Web Text)

Max Activating Token Index: 167

Text #14

Max Range: 3.0854. Min Range: -3.0854

Max Act: 2.9026. Min Act: -0.1700

Data Index: 4784910 (Open Web Text)

Max Activating Token Index: 1019

Text #15

Max Range: 3.0854. Min Range: -3.0854

Max Act: 2.8959. Min Act: -0.1700

Data Index: 1810799 (Open Web Text)

Max Activating Token Index: 927

Text #16

Max Range: 3.0854. Min Range: -3.0854

Max Act: 2.8819. Min Act: -0.1700

Data Index: 7202729 (Open Web Text)

Max Activating Token Index: 727

Text #17

Max Range: 3.0854. Min Range: -3.0854

Max Act: 2.8692. Min Act: -0.1700

Data Index: 8102962 (Open Web Text)

Max Activating Token Index: 338

Text #18

Max Range: 3.0854. Min Range: -3.0854

Max Act: 2.8482. Min Act: -0.1700

Data Index: 3994572 (Open Web Text)

Max Activating Token Index: 192

Text #19

Max Range: 3.0854. Min Range: -3.0854

Max Act: 2.8676. Min Act: -0.1700

Data Index: 327906 (Open Web Text)

Max Activating Token Index: 279