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

Dataset: Open Web Text

Neuron 1428 in Layer 1

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: 1.5692. Min Range: -1.5692

Max Act: 1.5692. Min Act: -0.1699

Data Index: 5110251 (Open Web Text)

Max Activating Token Index: 198

Text #1

Max Range: 1.5692. Min Range: -1.5692

Max Act: 1.5581. Min Act: -0.1699

Data Index: 607912 (Open Web Text)

Max Activating Token Index: 648

Text #2

Max Range: 1.5692. Min Range: -1.5692

Max Act: 1.5480. Min Act: -0.1570

Data Index: 1423933 (Open Web Text)

Max Activating Token Index: 823

Text #3

Max Range: 1.5692. Min Range: -1.5692

Max Act: 1.5451. Min Act: -0.1700

Data Index: 3962139 (Open Web Text)

Max Activating Token Index: 403

Text #4

Max Range: 1.5692. Min Range: -1.5692

Max Act: 1.5346. Min Act: -0.1562

Data Index: 6116866 (Open Web Text)

Max Activating Token Index: 299

Text #5

Max Range: 1.5692. Min Range: -1.5692

Max Act: 1.5381. Min Act: -0.1696

Data Index: 6834389 (Open Web Text)

Max Activating Token Index: 1016

Text #6

Max Range: 1.5692. Min Range: -1.5692

Max Act: 1.5303. Min Act: -0.1695

Data Index: 6980486 (Open Web Text)

Max Activating Token Index: 600

Text #7

Max Range: 1.5692. Min Range: -1.5692

Max Act: 1.5232. Min Act: -0.1700

Data Index: 6529640 (Open Web Text)

Max Activating Token Index: 405

Text #8

Max Range: 1.5692. Min Range: -1.5692

Max Act: 1.5271. Min Act: -0.1700

Data Index: 7915083 (Open Web Text)

Max Activating Token Index: 102

Text #9

Max Range: 1.5692. Min Range: -1.5692

Max Act: 1.5351. Min Act: -0.1674

Data Index: 8227381 (Open Web Text)

Max Activating Token Index: 353

Text #10

Max Range: 1.5692. Min Range: -1.5692

Max Act: 1.5059. Min Act: -0.1697

Data Index: 5868102 (Open Web Text)

Max Activating Token Index: 539

Text #11

Max Range: 1.5692. Min Range: -1.5692

Max Act: 1.5114. Min Act: -0.1700

Data Index: 2896737 (Open Web Text)

Max Activating Token Index: 715

Text #12

Max Range: 1.5692. Min Range: -1.5692

Max Act: 1.5162. Min Act: -0.1698

Data Index: 6582743 (Open Web Text)

Max Activating Token Index: 768

Text #13

Max Range: 1.5692. Min Range: -1.5692

Max Act: 1.5117. Min Act: -0.1700

Data Index: 1206467 (Open Web Text)

Max Activating Token Index: 736

Text #14

Max Range: 1.5692. Min Range: -1.5692

Max Act: 1.5087. Min Act: -0.1698

Data Index: 488399 (Open Web Text)

Max Activating Token Index: 640

Text #15

Max Range: 1.5692. Min Range: -1.5692

Max Act: 1.5124. Min Act: -0.1700

Data Index: 3299451 (Open Web Text)

Max Activating Token Index: 481

Text #16

Max Range: 1.5692. Min Range: -1.5692

Max Act: 1.5203. Min Act: -0.1692

Data Index: 2874413 (Open Web Text)

Max Activating Token Index: 841

Text #17

Max Range: 1.5692. Min Range: -1.5692

Max Act: 1.5065. Min Act: -0.1700

Data Index: 6528283 (Open Web Text)

Max Activating Token Index: 623

Text #18

Max Range: 1.5692. Min Range: -1.5692

Max Act: 1.5013. Min Act: -0.1696

Data Index: 4511759 (Open Web Text)

Max Activating Token Index: 655

Text #19

Max Range: 1.5692. Min Range: -1.5692

Max Act: 1.5075. Min Act: -0.1699

Data Index: 4476100 (Open Web Text)

Max Activating Token Index: 285