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

Dataset: Open Web Text

Neuron 2580 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: 4.7029. Min Range: -4.7029

Max Act: 4.7029. Min Act: -0.1700

Data Index: 2231402 (Open Web Text)

Max Activating Token Index: 547

Text #1

Max Range: 4.7029. Min Range: -4.7029

Max Act: 4.6753. Min Act: -0.1700

Data Index: 7701711 (Open Web Text)

Max Activating Token Index: 992

Text #2

Max Range: 4.7029. Min Range: -4.7029

Max Act: 4.6214. Min Act: -0.1700

Data Index: 7618156 (Open Web Text)

Max Activating Token Index: 559

Text #3

Max Range: 4.7029. Min Range: -4.7029

Max Act: 4.6130. Min Act: -0.1700

Data Index: 4084042 (Open Web Text)

Max Activating Token Index: 1008

Text #4

Max Range: 4.7029. Min Range: -4.7029

Max Act: 4.6315. Min Act: -0.1700

Data Index: 2102526 (Open Web Text)

Max Activating Token Index: 940

Text #5

Max Range: 4.7029. Min Range: -4.7029

Max Act: 4.6076. Min Act: -0.1700

Data Index: 3508400 (Open Web Text)

Max Activating Token Index: 31

Text #6

Max Range: 4.7029. Min Range: -4.7029

Max Act: 4.6055. Min Act: -0.1700

Data Index: 5183105 (Open Web Text)

Max Activating Token Index: 336

Text #7

Max Range: 4.7029. Min Range: -4.7029

Max Act: 4.5494. Min Act: -0.1700

Data Index: 7007152 (Open Web Text)

Max Activating Token Index: 65

Text #8

Max Range: 4.7029. Min Range: -4.7029

Max Act: 4.5702. Min Act: -0.1700

Data Index: 2746671 (Open Web Text)

Max Activating Token Index: 750

Text #9

Max Range: 4.7029. Min Range: -4.7029

Max Act: 4.5062. Min Act: -0.1700

Data Index: 1667136 (Open Web Text)

Max Activating Token Index: 209

Text #10

Max Range: 4.7029. Min Range: -4.7029

Max Act: 4.5534. Min Act: -0.1700

Data Index: 1229099 (Open Web Text)

Max Activating Token Index: 788

Text #11

Max Range: 4.7029. Min Range: -4.7029

Max Act: 4.4811. Min Act: -0.1700

Data Index: 7948317 (Open Web Text)

Max Activating Token Index: 827

Text #12

Max Range: 4.7029. Min Range: -4.7029

Max Act: 4.4915. Min Act: -0.1700

Data Index: 8407646 (Open Web Text)

Max Activating Token Index: 254

Text #13

Max Range: 4.7029. Min Range: -4.7029

Max Act: 4.4295. Min Act: -0.1700

Data Index: 4973036 (Open Web Text)

Max Activating Token Index: 54

Text #14

Max Range: 4.7029. Min Range: -4.7029

Max Act: 4.5036. Min Act: -0.1700

Data Index: 7209584 (Open Web Text)

Max Activating Token Index: 76

Text #15

Max Range: 4.7029. Min Range: -4.7029

Max Act: 4.4945. Min Act: -0.1700

Data Index: 2356017 (Open Web Text)

Max Activating Token Index: 43

Text #16

Max Range: 4.7029. Min Range: -4.7029

Max Act: 4.4548. Min Act: -0.1700

Data Index: 5768755 (Open Web Text)

Max Activating Token Index: 1011

Text #17

Max Range: 4.7029. Min Range: -4.7029

Max Act: 4.4762. Min Act: -0.1700

Data Index: 3635008 (Open Web Text)

Max Activating Token Index: 1010

Text #18

Max Range: 4.7029. Min Range: -4.7029

Max Act: 4.4427. Min Act: -0.1700

Data Index: 2101513 (Open Web Text)

Max Activating Token Index: 154

Text #19

Max Range: 4.7029. Min Range: -4.7029

Max Act: 4.4799. Min Act: -0.1700

Data Index: 5882112 (Open Web Text)

Max Activating Token Index: 742