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

Dataset: Open Web Text

Neuron 406 in Layer 1

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: 2.0005. Min Range: -2.0005

Max Act: 2.0005. Min Act: -0.1700

Data Index: 7433081 (Open Web Text)

Max Activating Token Index: 682

Text #1

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.9201. Min Act: -0.1700

Data Index: 1303414 (Open Web Text)

Max Activating Token Index: 591

Text #2

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.9189. Min Act: -0.1700

Data Index: 1038718 (Open Web Text)

Max Activating Token Index: 910

Text #3

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.8984. Min Act: -0.1700

Data Index: 2218832 (Open Web Text)

Max Activating Token Index: 27

Text #4

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.8832. Min Act: -0.1700

Data Index: 464864 (Open Web Text)

Max Activating Token Index: 727

Text #5

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.8869. Min Act: -0.1700

Data Index: 5901785 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.8857. Min Act: -0.1700

Data Index: 7594841 (Open Web Text)

Max Activating Token Index: 807

Text #7

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.8853. Min Act: -0.1700

Data Index: 8703272 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.8817. Min Act: -0.1700

Data Index: 5135582 (Open Web Text)

Max Activating Token Index: 676

Text #9

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.8971. Min Act: -0.1700

Data Index: 6481095 (Open Web Text)

Max Activating Token Index: 22

Text #10

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.8723. Min Act: -0.1700

Data Index: 5391800 (Open Web Text)

Max Activating Token Index: 522

Text #11

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.8653. Min Act: -0.1700

Data Index: 7843029 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.8812. Min Act: -0.1700

Data Index: 7624664 (Open Web Text)

Max Activating Token Index: 1018

Text #13

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.8759. Min Act: -0.1700

Data Index: 3750751 (Open Web Text)

Max Activating Token Index: 353

Text #14

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.8625. Min Act: -0.1700

Data Index: 7452642 (Open Web Text)

Max Activating Token Index: 568

Text #15

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.8624. Min Act: -0.1700

Data Index: 4100719 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.8608. Min Act: -0.1700

Data Index: 1699867 (Open Web Text)

Max Activating Token Index: 321

Text #17

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.8574. Min Act: -0.1700

Data Index: 5530300 (Open Web Text)

Max Activating Token Index: 833

Text #18

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.8521. Min Act: -0.1700

Data Index: 5758549 (Open Web Text)

Max Activating Token Index: 1018

Text #19

Max Range: 2.0005. Min Range: -2.0005

Max Act: 1.8577. Min Act: -0.1700

Data Index: 5898273 (Open Web Text)

Max Activating Token Index: 5