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

Dataset: Open Web Text

Neuron 904 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: 3.1822. Min Range: -3.1822

Max Act: 3.1822. Min Act: -0.1700

Data Index: 390738 (Open Web Text)

Max Activating Token Index: 570

Text #1

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.1660. Min Act: -0.1700

Data Index: 1630787 (Open Web Text)

Max Activating Token Index: 788

Text #2

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.1363. Min Act: -0.1700

Data Index: 4839159 (Open Web Text)

Max Activating Token Index: 460

Text #3

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.1337. Min Act: -0.1700

Data Index: 913539 (Open Web Text)

Max Activating Token Index: 467

Text #4

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.1206. Min Act: -0.1700

Data Index: 3823918 (Open Web Text)

Max Activating Token Index: 461

Text #5

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.0812. Min Act: -0.1700

Data Index: 119655 (Open Web Text)

Max Activating Token Index: 123

Text #6

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.1172. Min Act: -0.1700

Data Index: 1918722 (Open Web Text)

Max Activating Token Index: 678

Text #7

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.0821. Min Act: -0.1700

Data Index: 6553193 (Open Web Text)

Max Activating Token Index: 346

Text #8

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.0759. Min Act: -0.1700

Data Index: 4065375 (Open Web Text)

Max Activating Token Index: 790

Text #9

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.0658. Min Act: -0.1700

Data Index: 978917 (Open Web Text)

Max Activating Token Index: 1010

Text #10

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.0717. Min Act: -0.1700

Data Index: 1730137 (Open Web Text)

Max Activating Token Index: 886

Text #11

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.0789. Min Act: -0.1700

Data Index: 3986104 (Open Web Text)

Max Activating Token Index: 262

Text #12

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.0795. Min Act: -0.1700

Data Index: 6567336 (Open Web Text)

Max Activating Token Index: 923

Text #13

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.0855. Min Act: -0.1700

Data Index: 8264816 (Open Web Text)

Max Activating Token Index: 509

Text #14

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.0629. Min Act: -0.1700

Data Index: 7788645 (Open Web Text)

Max Activating Token Index: 618

Text #15

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.0684. Min Act: -0.1700

Data Index: 142725 (Open Web Text)

Max Activating Token Index: 520

Text #16

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.0782. Min Act: -0.1700

Data Index: 348774 (Open Web Text)

Max Activating Token Index: 801

Text #17

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.0905. Min Act: -0.1700

Data Index: 7760810 (Open Web Text)

Max Activating Token Index: 438

Text #18

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.0452. Min Act: -0.1700

Data Index: 3873528 (Open Web Text)

Max Activating Token Index: 655

Text #19

Max Range: 3.1822. Min Range: -3.1822

Max Act: 3.0575. Min Act: -0.1700

Data Index: 5274781 (Open Web Text)

Max Activating Token Index: 591