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

Dataset: Open Web Text

Neuron 134 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: 1.9232. Min Range: -1.9232

Max Act: 1.9232. Min Act: -0.1692

Data Index: 7007144 (Open Web Text)

Max Activating Token Index: 689

Text #1

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.9095. Min Act: -0.1700

Data Index: 1085561 (Open Web Text)

Max Activating Token Index: 885

Text #2

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.8983. Min Act: -0.1700

Data Index: 7699760 (Open Web Text)

Max Activating Token Index: 772

Text #3

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.8900. Min Act: -0.1699

Data Index: 7344447 (Open Web Text)

Max Activating Token Index: 823

Text #4

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.8903. Min Act: -0.1697

Data Index: 4099531 (Open Web Text)

Max Activating Token Index: 821

Text #5

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.8898. Min Act: -0.1700

Data Index: 4751566 (Open Web Text)

Max Activating Token Index: 672

Text #6

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.8963. Min Act: -0.1700

Data Index: 7899672 (Open Web Text)

Max Activating Token Index: 590

Text #7

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.8802. Min Act: -0.1700

Data Index: 3001055 (Open Web Text)

Max Activating Token Index: 305

Text #8

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.8851. Min Act: -0.1698

Data Index: 5158391 (Open Web Text)

Max Activating Token Index: 518

Text #9

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.8801. Min Act: -0.1698

Data Index: 4633103 (Open Web Text)

Max Activating Token Index: 286

Text #10

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.8864. Min Act: -0.1700

Data Index: 8072706 (Open Web Text)

Max Activating Token Index: 679

Text #11

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.8794. Min Act: -0.1698

Data Index: 6249505 (Open Web Text)

Max Activating Token Index: 564

Text #12

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.8841. Min Act: -0.1699

Data Index: 7544693 (Open Web Text)

Max Activating Token Index: 745

Text #13

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.8789. Min Act: -0.1700

Data Index: 7530228 (Open Web Text)

Max Activating Token Index: 688

Text #14

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.8770. Min Act: -0.1699

Data Index: 5594438 (Open Web Text)

Max Activating Token Index: 766

Text #15

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.8864. Min Act: -0.1697

Data Index: 7223333 (Open Web Text)

Max Activating Token Index: 788

Text #16

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.8766. Min Act: -0.1700

Data Index: 6320416 (Open Web Text)

Max Activating Token Index: 383

Text #17

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.8723. Min Act: -0.1698

Data Index: 1085562 (Open Web Text)

Max Activating Token Index: 830

Text #18

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.8794. Min Act: -0.1691

Data Index: 565891 (Open Web Text)

Max Activating Token Index: 54

Text #19

Max Range: 1.9232. Min Range: -1.9232

Max Act: 1.8730. Min Act: -0.1691

Data Index: 6535185 (Open Web Text)

Max Activating Token Index: 27