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

Dataset: Open Web Text

Neuron 938 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: 1.7735. Min Range: -1.7735

Max Act: 1.7735. Min Act: -0.1700

Data Index: 250558 (Open Web Text)

Max Activating Token Index: 88

Text #1

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7532. Min Act: -0.1698

Data Index: 3352288 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7600. Min Act: -0.1698

Data Index: 3967340 (Open Web Text)

Max Activating Token Index: 660

Text #3

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7621. Min Act: -0.1682

Data Index: 1248883 (Open Web Text)

Max Activating Token Index: 235

Text #4

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7531. Min Act: -0.1698

Data Index: 5610299 (Open Web Text)

Max Activating Token Index: 249

Text #5

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7481. Min Act: -0.1700

Data Index: 1124668 (Open Web Text)

Max Activating Token Index: 652

Text #6

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7585. Min Act: -0.1699

Data Index: 6043805 (Open Web Text)

Max Activating Token Index: 111

Text #7

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7527. Min Act: -0.1682

Data Index: 1689758 (Open Web Text)

Max Activating Token Index: 19

Text #8

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7510. Min Act: -0.1696

Data Index: 2044513 (Open Web Text)

Max Activating Token Index: 625

Text #9

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7462. Min Act: -0.1662

Data Index: 2281404 (Open Web Text)

Max Activating Token Index: 96

Text #10

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7438. Min Act: -0.1685

Data Index: 3368436 (Open Web Text)

Max Activating Token Index: 640

Text #11

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7372. Min Act: -0.1690

Data Index: 1378484 (Open Web Text)

Max Activating Token Index: 110

Text #12

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7321. Min Act: -0.1698

Data Index: 2192389 (Open Web Text)

Max Activating Token Index: 395

Text #13

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7240. Min Act: -0.1700

Data Index: 5280440 (Open Web Text)

Max Activating Token Index: 652

Text #14

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7360. Min Act: -0.1700

Data Index: 1801797 (Open Web Text)

Max Activating Token Index: 76

Text #15

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7274. Min Act: -0.1678

Data Index: 4768288 (Open Web Text)

Max Activating Token Index: 89

Text #16

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7229. Min Act: -0.1693

Data Index: 1438114 (Open Web Text)

Max Activating Token Index: 596

Text #17

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7211. Min Act: -0.1649

Data Index: 1322279 (Open Web Text)

Max Activating Token Index: 718

Text #18

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7249. Min Act: -0.1700

Data Index: 5471312 (Open Web Text)

Max Activating Token Index: 720

Text #19

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7245. Min Act: -0.1628

Data Index: 6324611 (Open Web Text)

Max Activating Token Index: 46