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

Dataset: Open Web Text

Neuron 1762 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: 3.8794. Min Range: -3.8794

Max Act: 3.8794. Min Act: -0.1700

Data Index: 8245108 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.7789. Min Act: -0.1700

Data Index: 6933866 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.6910. Min Act: -0.1700

Data Index: 8243593 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.6666. Min Act: -0.1700

Data Index: 3503907 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.6487. Min Act: -0.1700

Data Index: 7151364 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.5830. Min Act: -0.1700

Data Index: 5053679 (Open Web Text)

Max Activating Token Index: 760

Text #6

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.6714. Min Act: -0.1700

Data Index: 968141 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.5693. Min Act: -0.1700

Data Index: 6896451 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.5250. Min Act: -0.1700

Data Index: 1308144 (Open Web Text)

Max Activating Token Index: 104

Text #9

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.4859. Min Act: -0.1700

Data Index: 2628921 (Open Web Text)

Max Activating Token Index: 703

Text #10

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.4651. Min Act: -0.1700

Data Index: 1308145 (Open Web Text)

Max Activating Token Index: 196

Text #11

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.4510. Min Act: -0.1700

Data Index: 5423931 (Open Web Text)

Max Activating Token Index: 290

Text #12

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.4715. Min Act: -0.1700

Data Index: 4335469 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.4255. Min Act: -0.1700

Data Index: 1710815 (Open Web Text)

Max Activating Token Index: 277

Text #14

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.4643. Min Act: -0.1700

Data Index: 2495348 (Open Web Text)

Max Activating Token Index: 372

Text #15

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.4263. Min Act: -0.1700

Data Index: 5423932 (Open Web Text)

Max Activating Token Index: 228

Text #16

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.4042. Min Act: -0.1700

Data Index: 1883358 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.4152. Min Act: -0.1700

Data Index: 5423929 (Open Web Text)

Max Activating Token Index: 766

Text #18

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.3713. Min Act: -0.1700

Data Index: 2007120 (Open Web Text)

Max Activating Token Index: 661

Text #19

Max Range: 3.8794. Min Range: -3.8794

Max Act: 3.3839. Min Act: -0.1700

Data Index: 3913236 (Open Web Text)

Max Activating Token Index: 3