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

Dataset: Open Web Text

Neuron 815 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: 3.4644. Min Range: -3.4644

Max Act: 3.4644. Min Act: -0.1700

Data Index: 2462221 (Open Web Text)

Max Activating Token Index: 196

Text #1

Max Range: 3.4644. Min Range: -3.4644

Max Act: 3.4154. Min Act: -0.1700

Data Index: 5801523 (Open Web Text)

Max Activating Token Index: 66

Text #2

Max Range: 3.4644. Min Range: -3.4644

Max Act: 3.3883. Min Act: -0.1700

Data Index: 5801530 (Open Web Text)

Max Activating Token Index: 157

Text #3

Max Range: 3.4644. Min Range: -3.4644

Max Act: 3.3908. Min Act: -0.1700

Data Index: 2462227 (Open Web Text)

Max Activating Token Index: 362

Text #4

Max Range: 3.4644. Min Range: -3.4644

Max Act: 3.3753. Min Act: -0.1700

Data Index: 8765346 (Open Web Text)

Max Activating Token Index: 70

Text #5

Max Range: 3.4644. Min Range: -3.4644

Max Act: 3.3678. Min Act: -0.1700

Data Index: 8781147 (Open Web Text)

Max Activating Token Index: 510

Text #6

Max Range: 3.4644. Min Range: -3.4644

Max Act: 3.3697. Min Act: -0.1700

Data Index: 4926805 (Open Web Text)

Max Activating Token Index: 326

Text #7

Max Range: 3.4644. Min Range: -3.4644

Max Act: 3.3750. Min Act: -0.1700

Data Index: 3604980 (Open Web Text)

Max Activating Token Index: 212

Text #8

Max Range: 3.4644. Min Range: -3.4644

Max Act: 3.3602. Min Act: -0.1700

Data Index: 6920500 (Open Web Text)

Max Activating Token Index: 819

Text #9

Max Range: 3.4644. Min Range: -3.4644

Max Act: 3.3809. Min Act: -0.1700

Data Index: 3604964 (Open Web Text)

Max Activating Token Index: 750

Text #10

Max Range: 3.4644. Min Range: -3.4644

Max Act: 3.3817. Min Act: -0.1700

Data Index: 3560473 (Open Web Text)

Max Activating Token Index: 641

Text #11

Max Range: 3.4644. Min Range: -3.4644

Max Act: 3.3458. Min Act: -0.1700

Data Index: 8128943 (Open Web Text)

Max Activating Token Index: 579

Text #12

Max Range: 3.4644. Min Range: -3.4644

Max Act: 3.3635. Min Act: -0.1700

Data Index: 8128929 (Open Web Text)

Max Activating Token Index: 708

Text #13

Max Range: 3.4644. Min Range: -3.4644

Max Act: 3.3591. Min Act: -0.1700

Data Index: 8128927 (Open Web Text)

Max Activating Token Index: 155

Text #14

Max Range: 3.4644. Min Range: -3.4644

Max Act: 3.3754. Min Act: -0.1700

Data Index: 7165418 (Open Web Text)

Max Activating Token Index: 644

Text #15

Max Range: 3.4644. Min Range: -3.4644

Max Act: 3.3551. Min Act: -0.1700

Data Index: 5158124 (Open Web Text)

Max Activating Token Index: 130

Text #16

Max Range: 3.4644. Min Range: -3.4644

Max Act: 3.3563. Min Act: -0.1700

Data Index: 2289720 (Open Web Text)

Max Activating Token Index: 377

Text #17

Max Range: 3.4644. Min Range: -3.4644

Max Act: 3.3488. Min Act: -0.1700

Data Index: 6920486 (Open Web Text)

Max Activating Token Index: 354

Text #18

Max Range: 3.4644. Min Range: -3.4644

Max Act: 3.3562. Min Act: -0.1700

Data Index: 3378114 (Open Web Text)

Max Activating Token Index: 470

Text #19

Max Range: 3.4644. Min Range: -3.4644

Max Act: 3.3521. Min Act: -0.1700

Data Index: 2134562 (Open Web Text)

Max Activating Token Index: 498