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

Dataset: Open Web Text

Neuron 863 in Layer 4

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: 3.2878. Min Range: -3.2878

Max Act: 3.2878. Min Act: -0.1700

Data Index: 6078772 (Open Web Text)

Max Activating Token Index: 944

Text #1

Max Range: 3.2878. Min Range: -3.2878

Max Act: 3.2529. Min Act: -0.1700

Data Index: 2332388 (Open Web Text)

Max Activating Token Index: 144

Text #2

Max Range: 3.2878. Min Range: -3.2878

Max Act: 3.1862. Min Act: -0.1700

Data Index: 3926215 (Open Web Text)

Max Activating Token Index: 933

Text #3

Max Range: 3.2878. Min Range: -3.2878

Max Act: 3.1397. Min Act: -0.1700

Data Index: 4876967 (Open Web Text)

Max Activating Token Index: 164

Text #4

Max Range: 3.2878. Min Range: -3.2878

Max Act: 3.1394. Min Act: -0.1700

Data Index: 6394402 (Open Web Text)

Max Activating Token Index: 26

Text #5

Max Range: 3.2878. Min Range: -3.2878

Max Act: 3.1218. Min Act: -0.1700

Data Index: 4354421 (Open Web Text)

Max Activating Token Index: 866

Text #6

Max Range: 3.2878. Min Range: -3.2878

Max Act: 3.0809. Min Act: -0.1700

Data Index: 4750264 (Open Web Text)

Max Activating Token Index: 688

Text #7

Max Range: 3.2878. Min Range: -3.2878

Max Act: 3.1142. Min Act: -0.1700

Data Index: 5251906 (Open Web Text)

Max Activating Token Index: 83

Text #8

Max Range: 3.2878. Min Range: -3.2878

Max Act: 3.0729. Min Act: -0.1700

Data Index: 7802969 (Open Web Text)

Max Activating Token Index: 18

Text #9

Max Range: 3.2878. Min Range: -3.2878

Max Act: 3.0760. Min Act: -0.1700

Data Index: 2976463 (Open Web Text)

Max Activating Token Index: 394

Text #10

Max Range: 3.2878. Min Range: -3.2878

Max Act: 3.0652. Min Act: -0.1700

Data Index: 5220617 (Open Web Text)

Max Activating Token Index: 718

Text #11

Max Range: 3.2878. Min Range: -3.2878

Max Act: 3.0430. Min Act: -0.1700

Data Index: 4389895 (Open Web Text)

Max Activating Token Index: 889

Text #12

Max Range: 3.2878. Min Range: -3.2878

Max Act: 3.0511. Min Act: -0.1700

Data Index: 1509037 (Open Web Text)

Max Activating Token Index: 681

Text #13

Max Range: 3.2878. Min Range: -3.2878

Max Act: 3.0492. Min Act: -0.1700

Data Index: 4788739 (Open Web Text)

Max Activating Token Index: 684

Text #14

Max Range: 3.2878. Min Range: -3.2878

Max Act: 3.0358. Min Act: -0.1700

Data Index: 2701048 (Open Web Text)

Max Activating Token Index: 166

Text #15

Max Range: 3.2878. Min Range: -3.2878

Max Act: 2.9931. Min Act: -0.1700

Data Index: 327868 (Open Web Text)

Max Activating Token Index: 522

Text #16

Max Range: 3.2878. Min Range: -3.2878

Max Act: 2.9781. Min Act: -0.1700

Data Index: 1395053 (Open Web Text)

Max Activating Token Index: 721

Text #17

Max Range: 3.2878. Min Range: -3.2878

Max Act: 2.9992. Min Act: -0.1700

Data Index: 6608296 (Open Web Text)

Max Activating Token Index: 146

Text #18

Max Range: 3.2878. Min Range: -3.2878

Max Act: 3.0016. Min Act: -0.1700

Data Index: 5357438 (Open Web Text)

Max Activating Token Index: 684

Text #19

Max Range: 3.2878. Min Range: -3.2878

Max Act: 2.9704. Min Act: -0.1700

Data Index: 5662118 (Open Web Text)

Max Activating Token Index: 364