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

Dataset: Open Web Text

Neuron 2827 in Layer 4

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: 7.5677. Min Range: -7.5677

Max Act: 7.5677. Min Act: -0.1700

Data Index: 81074 (Open Web Text)

Max Activating Token Index: 606

Text #1

Max Range: 7.5677. Min Range: -7.5677

Max Act: 7.4054. Min Act: -0.1700

Data Index: 5165904 (Open Web Text)

Max Activating Token Index: 1012

Text #2

Max Range: 7.5677. Min Range: -7.5677

Max Act: 7.3525. Min Act: -0.1700

Data Index: 402487 (Open Web Text)

Max Activating Token Index: 564

Text #3

Max Range: 7.5677. Min Range: -7.5677

Max Act: 7.3652. Min Act: -0.1700

Data Index: 5935777 (Open Web Text)

Max Activating Token Index: 528

Text #4

Max Range: 7.5677. Min Range: -7.5677

Max Act: 7.2446. Min Act: -0.1700

Data Index: 1838595 (Open Web Text)

Max Activating Token Index: 546

Text #5

Max Range: 7.5677. Min Range: -7.5677

Max Act: 7.3637. Min Act: -0.1700

Data Index: 6880332 (Open Web Text)

Max Activating Token Index: 618

Text #6

Max Range: 7.5677. Min Range: -7.5677

Max Act: 7.2111. Min Act: -0.1700

Data Index: 1628569 (Open Web Text)

Max Activating Token Index: 739

Text #7

Max Range: 7.5677. Min Range: -7.5677

Max Act: 7.2128. Min Act: -0.1700

Data Index: 4844854 (Open Web Text)

Max Activating Token Index: 436

Text #8

Max Range: 7.5677. Min Range: -7.5677

Max Act: 7.1656. Min Act: -0.1700

Data Index: 5643457 (Open Web Text)

Max Activating Token Index: 274

Text #9

Max Range: 7.5677. Min Range: -7.5677

Max Act: 7.1315. Min Act: -0.1700

Data Index: 4354250 (Open Web Text)

Max Activating Token Index: 859

Text #10

Max Range: 7.5677. Min Range: -7.5677

Max Act: 7.1362. Min Act: -0.1700

Data Index: 4844852 (Open Web Text)

Max Activating Token Index: 486

Text #11

Max Range: 7.5677. Min Range: -7.5677

Max Act: 7.1051. Min Act: -0.1700

Data Index: 1458080 (Open Web Text)

Max Activating Token Index: 985

Text #12

Max Range: 7.5677. Min Range: -7.5677

Max Act: 7.1370. Min Act: -0.1700

Data Index: 819121 (Open Web Text)

Max Activating Token Index: 805

Text #13

Max Range: 7.5677. Min Range: -7.5677

Max Act: 7.0787. Min Act: -0.1700

Data Index: 301751 (Open Web Text)

Max Activating Token Index: 538

Text #14

Max Range: 7.5677. Min Range: -7.5677

Max Act: 7.1804. Min Act: -0.1700

Data Index: 3746606 (Open Web Text)

Max Activating Token Index: 430

Text #15

Max Range: 7.5677. Min Range: -7.5677

Max Act: 7.0996. Min Act: -0.1700

Data Index: 6249010 (Open Web Text)

Max Activating Token Index: 691

Text #16

Max Range: 7.5677. Min Range: -7.5677

Max Act: 7.0485. Min Act: -0.1700

Data Index: 7159815 (Open Web Text)

Max Activating Token Index: 928

Text #17

Max Range: 7.5677. Min Range: -7.5677

Max Act: 7.0287. Min Act: -0.1700

Data Index: 222296 (Open Web Text)

Max Activating Token Index: 808

Text #18

Max Range: 7.5677. Min Range: -7.5677

Max Act: 7.0382. Min Act: -0.1700

Data Index: 4738929 (Open Web Text)

Max Activating Token Index: 971

Text #19

Max Range: 7.5677. Min Range: -7.5677

Max Act: 6.9292. Min Act: -0.1700

Data Index: 5433660 (Open Web Text)

Max Activating Token Index: 348