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

Dataset: Open Web Text

Neuron 1729 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: 1.1643. Min Range: -1.1643

Max Act: 1.1643. Min Act: -0.1445

Data Index: 7412583 (Open Web Text)

Max Activating Token Index: 21

Text #1

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1536. Min Act: -0.1690

Data Index: 8003935 (Open Web Text)

Max Activating Token Index: 124

Text #2

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1574. Min Act: -0.1697

Data Index: 2635105 (Open Web Text)

Max Activating Token Index: 80

Text #3

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1588. Min Act: -0.1692

Data Index: 7039737 (Open Web Text)

Max Activating Token Index: 563

Text #4

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1580. Min Act: -0.1664

Data Index: 7634132 (Open Web Text)

Max Activating Token Index: 288

Text #5

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1602. Min Act: -0.1369

Data Index: 4880479 (Open Web Text)

Max Activating Token Index: 57

Text #6

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1546. Min Act: -0.1688

Data Index: 4739789 (Open Web Text)

Max Activating Token Index: 194

Text #7

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1510. Min Act: -0.1700

Data Index: 7646473 (Open Web Text)

Max Activating Token Index: 400

Text #8

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1429. Min Act: -0.1695

Data Index: 1806667 (Open Web Text)

Max Activating Token Index: 451

Text #9

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1480. Min Act: -0.1572

Data Index: 1063417 (Open Web Text)

Max Activating Token Index: 76

Text #10

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1433. Min Act: -0.1638

Data Index: 7397962 (Open Web Text)

Max Activating Token Index: 345

Text #11

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1509. Min Act: -0.1700

Data Index: 2437262 (Open Web Text)

Max Activating Token Index: 375

Text #12

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1492. Min Act: -0.1700

Data Index: 6510415 (Open Web Text)

Max Activating Token Index: 162

Text #13

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1454. Min Act: -0.1638

Data Index: 5726740 (Open Web Text)

Max Activating Token Index: 65

Text #14

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1296. Min Act: -0.1698

Data Index: 4475389 (Open Web Text)

Max Activating Token Index: 304

Text #15

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1382. Min Act: -0.1621

Data Index: 1056657 (Open Web Text)

Max Activating Token Index: 463

Text #16

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1380. Min Act: -0.1680

Data Index: 5405110 (Open Web Text)

Max Activating Token Index: 136

Text #17

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1335. Min Act: -0.1468

Data Index: 1759026 (Open Web Text)

Max Activating Token Index: 104

Text #18

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1372. Min Act: -0.1628

Data Index: 4121046 (Open Web Text)

Max Activating Token Index: 324

Text #19

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1384. Min Act: -0.1570

Data Index: 5606530 (Open Web Text)

Max Activating Token Index: 461