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

Dataset: Open Web Text

Neuron 1997 in Layer 6

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: 4.3829. Min Range: -4.3829

Max Act: 4.3829. Min Act: -0.1700

Data Index: 6701624 (Open Web Text)

Max Activating Token Index: 436

Text #1

Max Range: 4.3829. Min Range: -4.3829

Max Act: 4.3550. Min Act: -0.1700

Data Index: 1507959 (Open Web Text)

Max Activating Token Index: 994

Text #2

Max Range: 4.3829. Min Range: -4.3829

Max Act: 4.3521. Min Act: -0.1700

Data Index: 8154601 (Open Web Text)

Max Activating Token Index: 721

Text #3

Max Range: 4.3829. Min Range: -4.3829

Max Act: 4.3390. Min Act: -0.1700

Data Index: 4657280 (Open Web Text)

Max Activating Token Index: 440

Text #4

Max Range: 4.3829. Min Range: -4.3829

Max Act: 4.3456. Min Act: -0.1700

Data Index: 5265747 (Open Web Text)

Max Activating Token Index: 48

Text #5

Max Range: 4.3829. Min Range: -4.3829

Max Act: 4.3051. Min Act: -0.1700

Data Index: 3035422 (Open Web Text)

Max Activating Token Index: 892

Text #6

Max Range: 4.3829. Min Range: -4.3829

Max Act: 4.3131. Min Act: -0.1700

Data Index: 6835522 (Open Web Text)

Max Activating Token Index: 664

Text #7

Max Range: 4.3829. Min Range: -4.3829

Max Act: 4.3087. Min Act: -0.1700

Data Index: 5725133 (Open Web Text)

Max Activating Token Index: 694

Text #8

Max Range: 4.3829. Min Range: -4.3829

Max Act: 4.2905. Min Act: -0.1700

Data Index: 1678386 (Open Web Text)

Max Activating Token Index: 872

Text #9

Max Range: 4.3829. Min Range: -4.3829

Max Act: 4.3013. Min Act: -0.1700

Data Index: 8580437 (Open Web Text)

Max Activating Token Index: 863

Text #10

Max Range: 4.3829. Min Range: -4.3829

Max Act: 4.2884. Min Act: -0.1700

Data Index: 8202841 (Open Web Text)

Max Activating Token Index: 274

Text #11

Max Range: 4.3829. Min Range: -4.3829

Max Act: 4.2981. Min Act: -0.1700

Data Index: 2566003 (Open Web Text)

Max Activating Token Index: 719

Text #12

Max Range: 4.3829. Min Range: -4.3829

Max Act: 4.3036. Min Act: -0.1700

Data Index: 2024166 (Open Web Text)

Max Activating Token Index: 561

Text #13

Max Range: 4.3829. Min Range: -4.3829

Max Act: 4.2973. Min Act: -0.1700

Data Index: 5556583 (Open Web Text)

Max Activating Token Index: 277

Text #14

Max Range: 4.3829. Min Range: -4.3829

Max Act: 4.2816. Min Act: -0.1700

Data Index: 2747973 (Open Web Text)

Max Activating Token Index: 867

Text #15

Max Range: 4.3829. Min Range: -4.3829

Max Act: 4.2842. Min Act: -0.1700

Data Index: 2387759 (Open Web Text)

Max Activating Token Index: 789

Text #16

Max Range: 4.3829. Min Range: -4.3829

Max Act: 4.2805. Min Act: -0.1700

Data Index: 4381159 (Open Web Text)

Max Activating Token Index: 428

Text #17

Max Range: 4.3829. Min Range: -4.3829

Max Act: 4.2867. Min Act: -0.1700

Data Index: 139652 (Open Web Text)

Max Activating Token Index: 995

Text #18

Max Range: 4.3829. Min Range: -4.3829

Max Act: 4.2829. Min Act: -0.1700

Data Index: 593867 (Open Web Text)

Max Activating Token Index: 735

Text #19

Max Range: 4.3829. Min Range: -4.3829

Max Act: 4.3123. Min Act: -0.1700

Data Index: 2859168 (Open Web Text)

Max Activating Token Index: 713