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

Dataset: Open Web Text

Neuron 1934 in Layer 3

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: 4.6928. Min Range: -4.6928

Max Act: 4.6928. Min Act: -0.1700

Data Index: 945308 (Open Web Text)

Max Activating Token Index: 344

Text #1

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.6156. Min Act: -0.1700

Data Index: 3533493 (Open Web Text)

Max Activating Token Index: 994

Text #2

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.5841. Min Act: -0.1700

Data Index: 5176283 (Open Web Text)

Max Activating Token Index: 662

Text #3

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.5580. Min Act: -0.1700

Data Index: 628186 (Open Web Text)

Max Activating Token Index: 54

Text #4

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.5826. Min Act: -0.1700

Data Index: 1104616 (Open Web Text)

Max Activating Token Index: 131

Text #5

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.5288. Min Act: -0.1700

Data Index: 2434180 (Open Web Text)

Max Activating Token Index: 161

Text #6

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.5543. Min Act: -0.1700

Data Index: 7083101 (Open Web Text)

Max Activating Token Index: 740

Text #7

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.5199. Min Act: -0.1700

Data Index: 2905191 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.4915. Min Act: -0.1700

Data Index: 1277333 (Open Web Text)

Max Activating Token Index: 750

Text #9

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.5456. Min Act: -0.1700

Data Index: 4530626 (Open Web Text)

Max Activating Token Index: 400

Text #10

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.4898. Min Act: -0.1700

Data Index: 6731218 (Open Web Text)

Max Activating Token Index: 215

Text #11

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.4265. Min Act: -0.1700

Data Index: 3616530 (Open Web Text)

Max Activating Token Index: 999

Text #12

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.4635. Min Act: -0.1700

Data Index: 4377890 (Open Web Text)

Max Activating Token Index: 60

Text #13

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.4776. Min Act: -0.1700

Data Index: 6893505 (Open Web Text)

Max Activating Token Index: 657

Text #14

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.4535. Min Act: -0.1700

Data Index: 1430504 (Open Web Text)

Max Activating Token Index: 604

Text #15

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.4655. Min Act: -0.1700

Data Index: 7240686 (Open Web Text)

Max Activating Token Index: 720

Text #16

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.4167. Min Act: -0.1700

Data Index: 858881 (Open Web Text)

Max Activating Token Index: 820

Text #17

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.4235. Min Act: -0.1700

Data Index: 3604770 (Open Web Text)

Max Activating Token Index: 903

Text #18

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.4257. Min Act: -0.1700

Data Index: 1800150 (Open Web Text)

Max Activating Token Index: 112

Text #19

Max Range: 4.6928. Min Range: -4.6928

Max Act: 4.4323. Min Act: -0.1700

Data Index: 3445654 (Open Web Text)

Max Activating Token Index: 26