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

Dataset: Open Web Text

Neuron 945 in Layer 0

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: 4.9770. Min Range: -4.9770

Max Act: 4.9770. Min Act: -0.1700

Data Index: 2052056 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 4.9770. Min Range: -4.9770

Max Act: 4.9303. Min Act: -0.1700

Data Index: 5478176 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 4.9770. Min Range: -4.9770

Max Act: 4.9370. Min Act: -0.1700

Data Index: 6961194 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.9770. Min Range: -4.9770

Max Act: 4.9013. Min Act: -0.1700

Data Index: 2318879 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.9770. Min Range: -4.9770

Max Act: 4.9184. Min Act: -0.1700

Data Index: 2222176 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.9770. Min Range: -4.9770

Max Act: 4.9300. Min Act: -0.1700

Data Index: 603928 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 4.9770. Min Range: -4.9770

Max Act: 4.9030. Min Act: -0.1700

Data Index: 7922012 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.9770. Min Range: -4.9770

Max Act: 4.8965. Min Act: -0.1700

Data Index: 6109036 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 4.9770. Min Range: -4.9770

Max Act: 4.8799. Min Act: -0.1700

Data Index: 3093634 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.9770. Min Range: -4.9770

Max Act: 4.8808. Min Act: -0.1700

Data Index: 3532087 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 4.9770. Min Range: -4.9770

Max Act: 4.8890. Min Act: -0.1700

Data Index: 2029862 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 4.9770. Min Range: -4.9770

Max Act: 4.8635. Min Act: -0.1700

Data Index: 5112122 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.9770. Min Range: -4.9770

Max Act: 4.8417. Min Act: -0.1700

Data Index: 8641264 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.9770. Min Range: -4.9770

Max Act: 4.8543. Min Act: -0.1700

Data Index: 4903909 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 4.9770. Min Range: -4.9770

Max Act: 4.8441. Min Act: -0.1700

Data Index: 4398700 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.9770. Min Range: -4.9770

Max Act: 4.8656. Min Act: -0.1700

Data Index: 14658 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 4.9770. Min Range: -4.9770

Max Act: 4.8689. Min Act: -0.1700

Data Index: 7076301 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 4.9770. Min Range: -4.9770

Max Act: 4.8447. Min Act: -0.1700

Data Index: 6756301 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 4.9770. Min Range: -4.9770

Max Act: 4.8691. Min Act: -0.1700

Data Index: 3029659 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.9770. Min Range: -4.9770

Max Act: 4.8768. Min Act: -0.1700

Data Index: 2759661 (Open Web Text)

Max Activating Token Index: 7