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

Dataset: Open Web Text

Neuron 1452 in Layer 0

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: 1.7401. Min Range: -1.7401

Max Act: 1.7401. Min Act: -0.1412

Data Index: 6756235 (Open Web Text)

Max Activating Token Index: 358

Text #1

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.7138. Min Act: -0.1684

Data Index: 2363333 (Open Web Text)

Max Activating Token Index: 25

Text #2

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.7155. Min Act: -0.1399

Data Index: 681368 (Open Web Text)

Max Activating Token Index: 177

Text #3

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.6814. Min Act: -0.1399

Data Index: 2681483 (Open Web Text)

Max Activating Token Index: 707

Text #4

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.6639. Min Act: -0.1668

Data Index: 2014275 (Open Web Text)

Max Activating Token Index: 601

Text #5

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.6501. Min Act: -0.1496

Data Index: 3949217 (Open Web Text)

Max Activating Token Index: 213

Text #6

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.6500. Min Act: -0.1655

Data Index: 6334569 (Open Web Text)

Max Activating Token Index: 161

Text #7

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.6497. Min Act: -0.1461

Data Index: 4266848 (Open Web Text)

Max Activating Token Index: 653

Text #8

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.6520. Min Act: -0.1690

Data Index: 4606869 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.6435. Min Act: -0.1601

Data Index: 3200881 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.6501. Min Act: -0.1399

Data Index: 5845343 (Open Web Text)

Max Activating Token Index: 405

Text #11

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.6416. Min Act: -0.1399

Data Index: 4155440 (Open Web Text)

Max Activating Token Index: 120

Text #12

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.6423. Min Act: -0.1664

Data Index: 6862889 (Open Web Text)

Max Activating Token Index: 23

Text #13

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.6383. Min Act: -0.1671

Data Index: 7419836 (Open Web Text)

Max Activating Token Index: 783

Text #14

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.6313. Min Act: -0.1657

Data Index: 5316414 (Open Web Text)

Max Activating Token Index: 805

Text #15

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.6386. Min Act: -0.1586

Data Index: 7991385 (Open Web Text)

Max Activating Token Index: 903

Text #16

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.6350. Min Act: -0.1699

Data Index: 81894 (Open Web Text)

Max Activating Token Index: 795

Text #17

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.6364. Min Act: -0.1688

Data Index: 6844507 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.6258. Min Act: -0.1513

Data Index: 1536825 (Open Web Text)

Max Activating Token Index: 927

Text #19

Max Range: 1.7401. Min Range: -1.7401

Max Act: 1.6277. Min Act: -0.1618

Data Index: 1640834 (Open Web Text)

Max Activating Token Index: 699