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

Dataset: Open Web Text

Neuron 2805 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: 1.6736. Min Range: -1.6736

Max Act: 1.6736. Min Act: -0.1698

Data Index: 5832968 (Open Web Text)

Max Activating Token Index: 77

Text #1

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.6333. Min Act: -0.1694

Data Index: 6544913 (Open Web Text)

Max Activating Token Index: 910

Text #2

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.6156. Min Act: -0.1696

Data Index: 5506975 (Open Web Text)

Max Activating Token Index: 345

Text #3

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.6111. Min Act: -0.1700

Data Index: 6228706 (Open Web Text)

Max Activating Token Index: 919

Text #4

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.6190. Min Act: -0.1683

Data Index: 3099149 (Open Web Text)

Max Activating Token Index: 632

Text #5

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.6102. Min Act: -0.1700

Data Index: 1691809 (Open Web Text)

Max Activating Token Index: 369

Text #6

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.6012. Min Act: -0.1695

Data Index: 8219125 (Open Web Text)

Max Activating Token Index: 896

Text #7

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.5940. Min Act: -0.1552

Data Index: 7013733 (Open Web Text)

Max Activating Token Index: 179

Text #8

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.5896. Min Act: -0.1625

Data Index: 6273880 (Open Web Text)

Max Activating Token Index: 130

Text #9

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.5885. Min Act: -0.1697

Data Index: 5719203 (Open Web Text)

Max Activating Token Index: 522

Text #10

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.5922. Min Act: -0.1699

Data Index: 7516867 (Open Web Text)

Max Activating Token Index: 614

Text #11

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.5847. Min Act: -0.1664

Data Index: 7228014 (Open Web Text)

Max Activating Token Index: 72

Text #12

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.5820. Min Act: -0.1680

Data Index: 6089191 (Open Web Text)

Max Activating Token Index: 896

Text #13

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.5795. Min Act: -0.1595

Data Index: 3099150 (Open Web Text)

Max Activating Token Index: 536

Text #14

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.5801. Min Act: -0.1700

Data Index: 5476179 (Open Web Text)

Max Activating Token Index: 140

Text #15

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.5760. Min Act: -0.1700

Data Index: 4843520 (Open Web Text)

Max Activating Token Index: 678

Text #16

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.5779. Min Act: -0.1699

Data Index: 4843524 (Open Web Text)

Max Activating Token Index: 455

Text #17

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.5789. Min Act: -0.1685

Data Index: 2724996 (Open Web Text)

Max Activating Token Index: 448

Text #18

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.5672. Min Act: -0.1700

Data Index: 3195626 (Open Web Text)

Max Activating Token Index: 350

Text #19

Max Range: 1.6736. Min Range: -1.6736

Max Act: 1.5642. Min Act: -0.1475

Data Index: 1388085 (Open Web Text)

Max Activating Token Index: 358