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

Dataset: Open Web Text

Neuron 2944 in Layer 2

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: 5.9554. Min Range: -5.9554

Max Act: 5.9554. Min Act: -0.1700

Data Index: 5636662 (Open Web Text)

Max Activating Token Index: 19

Text #1

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.7639. Min Act: -0.1700

Data Index: 4230203 (Open Web Text)

Max Activating Token Index: 28

Text #2

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.4974. Min Act: -0.1700

Data Index: 2235828 (Open Web Text)

Max Activating Token Index: 26

Text #3

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.4813. Min Act: -0.1700

Data Index: 4744207 (Open Web Text)

Max Activating Token Index: 17

Text #4

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.3462. Min Act: -0.1700

Data Index: 1896631 (Open Web Text)

Max Activating Token Index: 44

Text #5

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.1974. Min Act: -0.1700

Data Index: 3189654 (Open Web Text)

Max Activating Token Index: 29

Text #6

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.2225. Min Act: -0.1700

Data Index: 2655660 (Open Web Text)

Max Activating Token Index: 52

Text #7

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.1420. Min Act: -0.1700

Data Index: 4205865 (Open Web Text)

Max Activating Token Index: 24

Text #8

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.0838. Min Act: -0.1700

Data Index: 7729937 (Open Web Text)

Max Activating Token Index: 35

Text #9

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.0873. Min Act: -0.1700

Data Index: 2686240 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.0947. Min Act: -0.1700

Data Index: 750536 (Open Web Text)

Max Activating Token Index: 15

Text #11

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.0521. Min Act: -0.1700

Data Index: 1691200 (Open Web Text)

Max Activating Token Index: 55

Text #12

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.0450. Min Act: -0.1700

Data Index: 3448247 (Open Web Text)

Max Activating Token Index: 18

Text #13

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.0555. Min Act: -0.1700

Data Index: 6602570 (Open Web Text)

Max Activating Token Index: 41

Text #14

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.0727. Min Act: -0.1700

Data Index: 3517602 (Open Web Text)

Max Activating Token Index: 18

Text #15

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.1024. Min Act: -0.1700

Data Index: 4823422 (Open Web Text)

Max Activating Token Index: 824

Text #16

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.0743. Min Act: -0.1700

Data Index: 7626669 (Open Web Text)

Max Activating Token Index: 48

Text #17

Max Range: 5.9554. Min Range: -5.9554

Max Act: 5.0284. Min Act: -0.1700

Data Index: 6287115 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 5.9554. Min Range: -5.9554

Max Act: 4.9554. Min Act: -0.1700

Data Index: 2274852 (Open Web Text)

Max Activating Token Index: 672

Text #19

Max Range: 5.9554. Min Range: -5.9554

Max Act: 4.9917. Min Act: -0.1700

Data Index: 5835923 (Open Web Text)

Max Activating Token Index: 14