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

Dataset: Open Web Text

Neuron 2224 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: 4.8770. Min Range: -4.8770

Max Act: 4.8770. Min Act: -0.1700

Data Index: 8713965 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.8516. Min Act: -0.1700

Data Index: 6015813 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.8620. Min Act: -0.1700

Data Index: 2501429 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.8065. Min Act: -0.1700

Data Index: 7808550 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.8103. Min Act: -0.1700

Data Index: 4527725 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.7563. Min Act: -0.1700

Data Index: 1651000 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.7736. Min Act: -0.1700

Data Index: 6980624 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.7850. Min Act: -0.1700

Data Index: 3779577 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.7627. Min Act: -0.1700

Data Index: 2978761 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.7793. Min Act: -0.1700

Data Index: 2112012 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.7710. Min Act: -0.1700

Data Index: 5705626 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.7644. Min Act: -0.1700

Data Index: 4935638 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.7276. Min Act: -0.1700

Data Index: 1491149 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.6983. Min Act: -0.1700

Data Index: 1759974 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.6854. Min Act: -0.1700

Data Index: 7892576 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.6940. Min Act: -0.1700

Data Index: 2537024 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.6917. Min Act: -0.1700

Data Index: 4581242 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.7176. Min Act: -0.1700

Data Index: 8065153 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.7142. Min Act: -0.1700

Data Index: 7655102 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.8770. Min Range: -4.8770

Max Act: 4.7142. Min Act: -0.1700

Data Index: 3921863 (Open Web Text)

Max Activating Token Index: 3