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

Dataset: Open Web Text

Neuron 289 in Layer 3

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: 4.3654. Min Range: -4.3654

Max Act: 4.3654. Min Act: -0.1700

Data Index: 1406544 (Open Web Text)

Max Activating Token Index: 837

Text #1

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.3621. Min Act: -0.1700

Data Index: 2372667 (Open Web Text)

Max Activating Token Index: 795

Text #2

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.2306. Min Act: -0.1700

Data Index: 3702099 (Open Web Text)

Max Activating Token Index: 615

Text #3

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.2508. Min Act: -0.1700

Data Index: 1884185 (Open Web Text)

Max Activating Token Index: 416

Text #4

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.2316. Min Act: -0.1700

Data Index: 1718713 (Open Web Text)

Max Activating Token Index: 925

Text #5

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.1823. Min Act: -0.1700

Data Index: 5596751 (Open Web Text)

Max Activating Token Index: 947

Text #6

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.1957. Min Act: -0.1700

Data Index: 2954011 (Open Web Text)

Max Activating Token Index: 815

Text #7

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.1741. Min Act: -0.1700

Data Index: 242451 (Open Web Text)

Max Activating Token Index: 443

Text #8

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.2082. Min Act: -0.1700

Data Index: 8260762 (Open Web Text)

Max Activating Token Index: 1002

Text #9

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.1826. Min Act: -0.1700

Data Index: 6688604 (Open Web Text)

Max Activating Token Index: 488

Text #10

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.1318. Min Act: -0.1700

Data Index: 8675590 (Open Web Text)

Max Activating Token Index: 213

Text #11

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.1880. Min Act: -0.1700

Data Index: 4391301 (Open Web Text)

Max Activating Token Index: 832

Text #12

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.1466. Min Act: -0.1700

Data Index: 1750697 (Open Web Text)

Max Activating Token Index: 327

Text #13

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.1573. Min Act: -0.1700

Data Index: 7390535 (Open Web Text)

Max Activating Token Index: 436

Text #14

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.1824. Min Act: -0.1700

Data Index: 1386591 (Open Web Text)

Max Activating Token Index: 231

Text #15

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.1796. Min Act: -0.1700

Data Index: 3358291 (Open Web Text)

Max Activating Token Index: 771

Text #16

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.1551. Min Act: -0.1700

Data Index: 6496805 (Open Web Text)

Max Activating Token Index: 751

Text #17

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.1237. Min Act: -0.1700

Data Index: 4610938 (Open Web Text)

Max Activating Token Index: 876

Text #18

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.1345. Min Act: -0.1700

Data Index: 4829418 (Open Web Text)

Max Activating Token Index: 484

Text #19

Max Range: 4.3654. Min Range: -4.3654

Max Act: 4.1282. Min Act: -0.1700

Data Index: 3550558 (Open Web Text)

Max Activating Token Index: 961