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

Dataset: Open Web Text

Neuron 10 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: 4.2780. Min Range: -4.2780

Max Act: 4.2780. Min Act: -0.1700

Data Index: 1293043 (Open Web Text)

Max Activating Token Index: 436

Text #1

Max Range: 4.2780. Min Range: -4.2780

Max Act: 4.2017. Min Act: -0.1700

Data Index: 5981308 (Open Web Text)

Max Activating Token Index: 49

Text #2

Max Range: 4.2780. Min Range: -4.2780

Max Act: 4.2289. Min Act: -0.1700

Data Index: 2990547 (Open Web Text)

Max Activating Token Index: 711

Text #3

Max Range: 4.2780. Min Range: -4.2780

Max Act: 4.1490. Min Act: -0.1700

Data Index: 7889686 (Open Web Text)

Max Activating Token Index: 380

Text #4

Max Range: 4.2780. Min Range: -4.2780

Max Act: 4.1568. Min Act: -0.1700

Data Index: 8630924 (Open Web Text)

Max Activating Token Index: 689

Text #5

Max Range: 4.2780. Min Range: -4.2780

Max Act: 4.1617. Min Act: -0.1700

Data Index: 8310067 (Open Web Text)

Max Activating Token Index: 473

Text #6

Max Range: 4.2780. Min Range: -4.2780

Max Act: 4.1613. Min Act: -0.1700

Data Index: 5442993 (Open Web Text)

Max Activating Token Index: 588

Text #7

Max Range: 4.2780. Min Range: -4.2780

Max Act: 4.1636. Min Act: -0.1700

Data Index: 6818906 (Open Web Text)

Max Activating Token Index: 818

Text #8

Max Range: 4.2780. Min Range: -4.2780

Max Act: 4.1401. Min Act: -0.1700

Data Index: 5143446 (Open Web Text)

Max Activating Token Index: 113

Text #9

Max Range: 4.2780. Min Range: -4.2780

Max Act: 4.1677. Min Act: -0.1700

Data Index: 3509899 (Open Web Text)

Max Activating Token Index: 352

Text #10

Max Range: 4.2780. Min Range: -4.2780

Max Act: 4.0993. Min Act: -0.1700

Data Index: 4586365 (Open Web Text)

Max Activating Token Index: 981

Text #11

Max Range: 4.2780. Min Range: -4.2780

Max Act: 4.1216. Min Act: -0.1700

Data Index: 2771432 (Open Web Text)

Max Activating Token Index: 891

Text #12

Max Range: 4.2780. Min Range: -4.2780

Max Act: 4.1167. Min Act: -0.1700

Data Index: 8310066 (Open Web Text)

Max Activating Token Index: 674

Text #13

Max Range: 4.2780. Min Range: -4.2780

Max Act: 4.1094. Min Act: -0.1700

Data Index: 7218078 (Open Web Text)

Max Activating Token Index: 760

Text #14

Max Range: 4.2780. Min Range: -4.2780

Max Act: 4.1062. Min Act: -0.1700

Data Index: 5309840 (Open Web Text)

Max Activating Token Index: 161

Text #15

Max Range: 4.2780. Min Range: -4.2780

Max Act: 4.0733. Min Act: -0.1700

Data Index: 2822636 (Open Web Text)

Max Activating Token Index: 972

Text #16

Max Range: 4.2780. Min Range: -4.2780

Max Act: 4.0736. Min Act: -0.1700

Data Index: 3554711 (Open Web Text)

Max Activating Token Index: 580

Text #17

Max Range: 4.2780. Min Range: -4.2780

Max Act: 4.0872. Min Act: -0.1700

Data Index: 7464914 (Open Web Text)

Max Activating Token Index: 84

Text #18

Max Range: 4.2780. Min Range: -4.2780

Max Act: 4.0905. Min Act: -0.1700

Data Index: 5253158 (Open Web Text)

Max Activating Token Index: 655

Text #19

Max Range: 4.2780. Min Range: -4.2780

Max Act: 4.0715. Min Act: -0.1700

Data Index: 3887203 (Open Web Text)

Max Activating Token Index: 326