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

Dataset: Open Web Text

Neuron 285 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: 6.2155. Min Range: -6.2155

Max Act: 6.2155. Min Act: -0.1700

Data Index: 6215742 (Open Web Text)

Max Activating Token Index: 934

Text #1

Max Range: 6.2155. Min Range: -6.2155

Max Act: 6.1441. Min Act: -0.1700

Data Index: 2809741 (Open Web Text)

Max Activating Token Index: 299

Text #2

Max Range: 6.2155. Min Range: -6.2155

Max Act: 6.1254. Min Act: -0.1700

Data Index: 663437 (Open Web Text)

Max Activating Token Index: 369

Text #3

Max Range: 6.2155. Min Range: -6.2155

Max Act: 6.1244. Min Act: -0.1700

Data Index: 6966942 (Open Web Text)

Max Activating Token Index: 328

Text #4

Max Range: 6.2155. Min Range: -6.2155

Max Act: 6.1039. Min Act: -0.1700

Data Index: 4008686 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 6.2155. Min Range: -6.2155

Max Act: 6.0854. Min Act: -0.1700

Data Index: 8659685 (Open Web Text)

Max Activating Token Index: 918

Text #6

Max Range: 6.2155. Min Range: -6.2155

Max Act: 6.0850. Min Act: -0.1700

Data Index: 981538 (Open Web Text)

Max Activating Token Index: 1008

Text #7

Max Range: 6.2155. Min Range: -6.2155

Max Act: 6.0841. Min Act: -0.1700

Data Index: 6820821 (Open Web Text)

Max Activating Token Index: 988

Text #8

Max Range: 6.2155. Min Range: -6.2155

Max Act: 6.0659. Min Act: -0.1700

Data Index: 8607793 (Open Web Text)

Max Activating Token Index: 573

Text #9

Max Range: 6.2155. Min Range: -6.2155

Max Act: 6.0736. Min Act: -0.1700

Data Index: 4386962 (Open Web Text)

Max Activating Token Index: 189

Text #10

Max Range: 6.2155. Min Range: -6.2155

Max Act: 6.0899. Min Act: -0.1700

Data Index: 7989891 (Open Web Text)

Max Activating Token Index: 549

Text #11

Max Range: 6.2155. Min Range: -6.2155

Max Act: 6.0695. Min Act: -0.1700

Data Index: 293751 (Open Web Text)

Max Activating Token Index: 317

Text #12

Max Range: 6.2155. Min Range: -6.2155

Max Act: 6.1077. Min Act: -0.1700

Data Index: 8687483 (Open Web Text)

Max Activating Token Index: 636

Text #13

Max Range: 6.2155. Min Range: -6.2155

Max Act: 6.0259. Min Act: -0.1700

Data Index: 1727279 (Open Web Text)

Max Activating Token Index: 588

Text #14

Max Range: 6.2155. Min Range: -6.2155

Max Act: 6.0640. Min Act: -0.1700

Data Index: 4254860 (Open Web Text)

Max Activating Token Index: 485

Text #15

Max Range: 6.2155. Min Range: -6.2155

Max Act: 6.0412. Min Act: -0.1700

Data Index: 1626648 (Open Web Text)

Max Activating Token Index: 29

Text #16

Max Range: 6.2155. Min Range: -6.2155

Max Act: 6.0269. Min Act: -0.1700

Data Index: 5066732 (Open Web Text)

Max Activating Token Index: 614

Text #17

Max Range: 6.2155. Min Range: -6.2155

Max Act: 6.0447. Min Act: -0.1700

Data Index: 7026717 (Open Web Text)

Max Activating Token Index: 472

Text #18

Max Range: 6.2155. Min Range: -6.2155

Max Act: 5.9787. Min Act: -0.1700

Data Index: 6833268 (Open Web Text)

Max Activating Token Index: 1007

Text #19

Max Range: 6.2155. Min Range: -6.2155

Max Act: 6.0304. Min Act: -0.1700

Data Index: 2374244 (Open Web Text)

Max Activating Token Index: 1013