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

Dataset: Open Web Text

Neuron 42 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: 1.6252. Min Range: -1.6252

Max Act: 1.6252. Min Act: -0.1395

Data Index: 3446213 (Open Web Text)

Max Activating Token Index: 336

Text #1

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5837. Min Act: -0.1399

Data Index: 3735647 (Open Web Text)

Max Activating Token Index: 545

Text #2

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5583. Min Act: -0.1395

Data Index: 8650323 (Open Web Text)

Max Activating Token Index: 533

Text #3

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5348. Min Act: -0.1468

Data Index: 3320733 (Open Web Text)

Max Activating Token Index: 584

Text #4

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5323. Min Act: -0.1516

Data Index: 5074281 (Open Web Text)

Max Activating Token Index: 779

Text #5

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5278. Min Act: -0.1395

Data Index: 7632865 (Open Web Text)

Max Activating Token Index: 510

Text #6

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5251. Min Act: -0.1442

Data Index: 8498103 (Open Web Text)

Max Activating Token Index: 509

Text #7

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5311. Min Act: -0.1405

Data Index: 681916 (Open Web Text)

Max Activating Token Index: 594

Text #8

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5220. Min Act: -0.1508

Data Index: 620009 (Open Web Text)

Max Activating Token Index: 613

Text #9

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5191. Min Act: -0.1486

Data Index: 1114416 (Open Web Text)

Max Activating Token Index: 961

Text #10

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5241. Min Act: -0.1489

Data Index: 5305666 (Open Web Text)

Max Activating Token Index: 688

Text #11

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5181. Min Act: -0.1561

Data Index: 5317632 (Open Web Text)

Max Activating Token Index: 402

Text #12

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5093. Min Act: -0.1395

Data Index: 302965 (Open Web Text)

Max Activating Token Index: 422

Text #13

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5078. Min Act: -0.1395

Data Index: 2393417 (Open Web Text)

Max Activating Token Index: 722

Text #14

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5074. Min Act: -0.1662

Data Index: 5124765 (Open Web Text)

Max Activating Token Index: 610

Text #15

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5084. Min Act: -0.1395

Data Index: 429887 (Open Web Text)

Max Activating Token Index: 345

Text #16

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5071. Min Act: -0.1546

Data Index: 2904033 (Open Web Text)

Max Activating Token Index: 524

Text #17

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5103. Min Act: -0.1449

Data Index: 6817375 (Open Web Text)

Max Activating Token Index: 596

Text #18

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5088. Min Act: -0.1544

Data Index: 5879288 (Open Web Text)

Max Activating Token Index: 417

Text #19

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5076. Min Act: -0.1395

Data Index: 4721538 (Open Web Text)

Max Activating Token Index: 303