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

Dataset: Open Web Text

Neuron 2979 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: 1.8901. Min Range: -1.8901

Max Act: 1.8901. Min Act: -0.1695

Data Index: 6316435 (Open Web Text)

Max Activating Token Index: 344

Text #1

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.8245. Min Act: -0.1689

Data Index: 4372103 (Open Web Text)

Max Activating Token Index: 573

Text #2

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.7876. Min Act: -0.1625

Data Index: 2675099 (Open Web Text)

Max Activating Token Index: 922

Text #3

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.7672. Min Act: -0.1698

Data Index: 4467092 (Open Web Text)

Max Activating Token Index: 374

Text #4

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.7713. Min Act: -0.1700

Data Index: 6609555 (Open Web Text)

Max Activating Token Index: 961

Text #5

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.7575. Min Act: -0.1565

Data Index: 6289653 (Open Web Text)

Max Activating Token Index: 622

Text #6

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.7470. Min Act: -0.1682

Data Index: 5842219 (Open Web Text)

Max Activating Token Index: 249

Text #7

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.7320. Min Act: -0.1700

Data Index: 4605914 (Open Web Text)

Max Activating Token Index: 810

Text #8

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.7264. Min Act: -0.1700

Data Index: 4453513 (Open Web Text)

Max Activating Token Index: 596

Text #9

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.7282. Min Act: -0.1700

Data Index: 8544788 (Open Web Text)

Max Activating Token Index: 225

Text #10

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.7203. Min Act: -0.1700

Data Index: 8479463 (Open Web Text)

Max Activating Token Index: 414

Text #11

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.7067. Min Act: -0.1699

Data Index: 5868915 (Open Web Text)

Max Activating Token Index: 656

Text #12

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.6984. Min Act: -0.1696

Data Index: 8319245 (Open Web Text)

Max Activating Token Index: 635

Text #13

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.7019. Min Act: -0.1700

Data Index: 3922775 (Open Web Text)

Max Activating Token Index: 394

Text #14

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.6904. Min Act: -0.1620

Data Index: 5526658 (Open Web Text)

Max Activating Token Index: 384

Text #15

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.6814. Min Act: -0.1699

Data Index: 6262708 (Open Web Text)

Max Activating Token Index: 855

Text #16

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.6755. Min Act: -0.1700

Data Index: 1037626 (Open Web Text)

Max Activating Token Index: 482

Text #17

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.6749. Min Act: -0.1700

Data Index: 3943747 (Open Web Text)

Max Activating Token Index: 658

Text #18

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.6797. Min Act: -0.1682

Data Index: 8184784 (Open Web Text)

Max Activating Token Index: 365

Text #19

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.6711. Min Act: -0.1698

Data Index: 3992376 (Open Web Text)

Max Activating Token Index: 527