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

Dataset: Open Web Text

Neuron 940 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: 1.0589. Min Range: -1.0589

Max Act: 1.0589. Min Act: -0.1697

Data Index: 2548764 (Open Web Text)

Max Activating Token Index: 40

Text #1

Max Range: 1.0589. Min Range: -1.0589

Max Act: 1.0253. Min Act: -0.1700

Data Index: 2109456 (Open Web Text)

Max Activating Token Index: 101

Text #2

Max Range: 1.0589. Min Range: -1.0589

Max Act: 1.0152. Min Act: -0.1700

Data Index: 4707129 (Open Web Text)

Max Activating Token Index: 638

Text #3

Max Range: 1.0589. Min Range: -1.0589

Max Act: 1.0003. Min Act: -0.1688

Data Index: 3585727 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9933. Min Act: -0.1691

Data Index: 3372069 (Open Web Text)

Max Activating Token Index: 112

Text #5

Max Range: 1.0589. Min Range: -1.0589

Max Act: 1.0014. Min Act: -0.1700

Data Index: 4275411 (Open Web Text)

Max Activating Token Index: 21

Text #6

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9985. Min Act: -0.1692

Data Index: 8390752 (Open Web Text)

Max Activating Token Index: 133

Text #7

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9834. Min Act: -0.1700

Data Index: 3930335 (Open Web Text)

Max Activating Token Index: 476

Text #8

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9948. Min Act: -0.1681

Data Index: 1345854 (Open Web Text)

Max Activating Token Index: 127

Text #9

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9877. Min Act: -0.1700

Data Index: 7215935 (Open Web Text)

Max Activating Token Index: 212

Text #10

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9907. Min Act: -0.1699

Data Index: 977708 (Open Web Text)

Max Activating Token Index: 15

Text #11

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9882. Min Act: -0.1700

Data Index: 5530273 (Open Web Text)

Max Activating Token Index: 401

Text #12

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9808. Min Act: -0.1695

Data Index: 1020774 (Open Web Text)

Max Activating Token Index: 17

Text #13

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9732. Min Act: -0.1700

Data Index: 1938346 (Open Web Text)

Max Activating Token Index: 143

Text #14

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9771. Min Act: -0.1700

Data Index: 8749426 (Open Web Text)

Max Activating Token Index: 623

Text #15

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9755. Min Act: -0.1700

Data Index: 8630661 (Open Web Text)

Max Activating Token Index: 22

Text #16

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9853. Min Act: -0.1700

Data Index: 6330581 (Open Web Text)

Max Activating Token Index: 71

Text #17

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9689. Min Act: -0.1700

Data Index: 2017634 (Open Web Text)

Max Activating Token Index: 209

Text #18

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9768. Min Act: -0.1700

Data Index: 3762079 (Open Web Text)

Max Activating Token Index: 202

Text #19

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9695. Min Act: -0.1700

Data Index: 2157140 (Open Web Text)

Max Activating Token Index: 95