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

Dataset: Open Web Text

Neuron 2530 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: 1.6506. Min Range: -1.6506

Max Act: 1.6488. Min Act: -0.1407

Data Index: 141353 (Open Web Text)

Max Activating Token Index: 63

Text #1

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.6506. Min Act: -0.1469

Data Index: 5516677 (Open Web Text)

Max Activating Token Index: 154

Text #2

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.6300. Min Act: -0.0897

Data Index: 141352 (Open Web Text)

Max Activating Token Index: 286

Text #3

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.6151. Min Act: -0.1431

Data Index: 6554701 (Open Web Text)

Max Activating Token Index: 575

Text #4

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.6033. Min Act: -0.1435

Data Index: 1888597 (Open Web Text)

Max Activating Token Index: 92

Text #5

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.5726. Min Act: -0.1694

Data Index: 5790053 (Open Web Text)

Max Activating Token Index: 116

Text #6

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.5675. Min Act: -0.1624

Data Index: 7685066 (Open Web Text)

Max Activating Token Index: 612

Text #7

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.5696. Min Act: -0.1700

Data Index: 2790495 (Open Web Text)

Max Activating Token Index: 588

Text #8

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.5610. Min Act: -0.1602

Data Index: 141351 (Open Web Text)

Max Activating Token Index: 911

Text #9

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.5628. Min Act: -0.1690

Data Index: 4673706 (Open Web Text)

Max Activating Token Index: 65

Text #10

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.5677. Min Act: -0.1644

Data Index: 6624139 (Open Web Text)

Max Activating Token Index: 344

Text #11

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.5609. Min Act: -0.1645

Data Index: 666130 (Open Web Text)

Max Activating Token Index: 552

Text #12

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.5545. Min Act: -0.1700

Data Index: 7428202 (Open Web Text)

Max Activating Token Index: 327

Text #13

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.5528. Min Act: -0.1693

Data Index: 1566551 (Open Web Text)

Max Activating Token Index: 138

Text #14

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.5601. Min Act: -0.1698

Data Index: 3850372 (Open Web Text)

Max Activating Token Index: 791

Text #15

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.5602. Min Act: -0.1638

Data Index: 1328608 (Open Web Text)

Max Activating Token Index: 71

Text #16

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.5594. Min Act: -0.1634

Data Index: 216556 (Open Web Text)

Max Activating Token Index: 79

Text #17

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.5492. Min Act: -0.1626

Data Index: 826381 (Open Web Text)

Max Activating Token Index: 662

Text #18

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.5409. Min Act: -0.1358

Data Index: 4463984 (Open Web Text)

Max Activating Token Index: 664

Text #19

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.5515. Min Act: -0.1376

Data Index: 6474259 (Open Web Text)

Max Activating Token Index: 977