Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 3799 in Layer 38

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.8320. Min Act: -0.1700

Data Index: 4418864 (Open Web Text)

Max Activating Token Index: 565

Text #1

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.7070. Min Act: -0.1700

Data Index: 8304273 (Open Web Text)

Max Activating Token Index: 468

Text #2

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.5508. Min Act: -0.1700

Data Index: 2104545 (Open Web Text)

Max Activating Token Index: 139

Text #3

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.5508. Min Act: -0.1700

Data Index: 4216287 (Open Web Text)

Max Activating Token Index: 554

Text #4

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.5195. Min Act: -0.1700

Data Index: 3140305 (Open Web Text)

Max Activating Token Index: 648

Text #5

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.4883. Min Act: -0.1700

Data Index: 2723576 (Open Web Text)

Max Activating Token Index: 515

Text #6

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.4883. Min Act: -0.1700

Data Index: 1717384 (Open Web Text)

Max Activating Token Index: 419

Text #7

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.3945. Min Act: -0.1700

Data Index: 1566344 (Open Web Text)

Max Activating Token Index: 170

Text #8

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.3320. Min Act: -0.1700

Data Index: 4735894 (Open Web Text)

Max Activating Token Index: 828

Text #9

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.3320. Min Act: -0.1700

Data Index: 1412372 (Open Web Text)

Max Activating Token Index: 132

Text #10

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.3008. Min Act: -0.1700

Data Index: 6665729 (Open Web Text)

Max Activating Token Index: 866

Text #11

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.3008. Min Act: -0.1700

Data Index: 3328212 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.2695. Min Act: -0.1700

Data Index: 1517015 (Open Web Text)

Max Activating Token Index: 93

Text #13

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.2695. Min Act: -0.1700

Data Index: 7576642 (Open Web Text)

Max Activating Token Index: 938

Text #14

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.2695. Min Act: -0.1700

Data Index: 509240 (Open Web Text)

Max Activating Token Index: 646

Text #15

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.2070. Min Act: -0.1700

Data Index: 6390546 (Open Web Text)

Max Activating Token Index: 121

Text #16

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.2070. Min Act: -0.1700

Data Index: 4703142 (Open Web Text)

Max Activating Token Index: 598

Text #17

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.2070. Min Act: -0.1700

Data Index: 3805242 (Open Web Text)

Max Activating Token Index: 283

Text #18

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.2070. Min Act: -0.1700

Data Index: 3883559 (Open Web Text)

Max Activating Token Index: 826

Text #19

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.2070. Min Act: -0.1700

Data Index: 5373116 (Open Web Text)

Max Activating Token Index: 644