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

Dataset: Open Web Text

Neuron 4978 in Layer 33

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7519. Min Range: -7.7519

Max Act: 7.7519. Min Act: -0.1700

Data Index: 3881584 (Open Web Text)

Max Activating Token Index: 932

Text #1

Max Range: 7.7519. Min Range: -7.7519

Max Act: 7.7519. Min Act: -0.1700

Data Index: 1244483 (Open Web Text)

Max Activating Token Index: 748

Text #2

Max Range: 7.7519. Min Range: -7.7519

Max Act: 7.6894. Min Act: -0.1700

Data Index: 2642988 (Open Web Text)

Max Activating Token Index: 482

Text #3

Max Range: 7.7519. Min Range: -7.7519

Max Act: 7.5331. Min Act: -0.1700

Data Index: 7612544 (Open Web Text)

Max Activating Token Index: 915

Text #4

Max Range: 7.7519. Min Range: -7.7519

Max Act: 7.4706. Min Act: -0.1700

Data Index: 882005 (Open Web Text)

Max Activating Token Index: 195

Text #5

Max Range: 7.7519. Min Range: -7.7519

Max Act: 7.4394. Min Act: -0.1700

Data Index: 7778932 (Open Web Text)

Max Activating Token Index: 665

Text #6

Max Range: 7.7519. Min Range: -7.7519

Max Act: 7.3144. Min Act: -0.1700

Data Index: 1054371 (Open Web Text)

Max Activating Token Index: 748

Text #7

Max Range: 7.7519. Min Range: -7.7519

Max Act: 7.2519. Min Act: -0.1700

Data Index: 6093202 (Open Web Text)

Max Activating Token Index: 643

Text #8

Max Range: 7.7519. Min Range: -7.7519

Max Act: 7.2831. Min Act: -0.1700

Data Index: 7495176 (Open Web Text)

Max Activating Token Index: 539

Text #9

Max Range: 7.7519. Min Range: -7.7519

Max Act: 7.2831. Min Act: -0.1700

Data Index: 350005 (Open Web Text)

Max Activating Token Index: 959

Text #10

Max Range: 7.7519. Min Range: -7.7519

Max Act: 7.1894. Min Act: -0.1700

Data Index: 7511824 (Open Web Text)

Max Activating Token Index: 447

Text #11

Max Range: 7.7519. Min Range: -7.7519

Max Act: 7.1581. Min Act: -0.1700

Data Index: 3127695 (Open Web Text)

Max Activating Token Index: 92

Text #12

Max Range: 7.7519. Min Range: -7.7519

Max Act: 7.1269. Min Act: -0.1700

Data Index: 379101 (Open Web Text)

Max Activating Token Index: 862

Text #13

Max Range: 7.7519. Min Range: -7.7519

Max Act: 7.1581. Min Act: -0.1700

Data Index: 2540106 (Open Web Text)

Max Activating Token Index: 1008

Text #14

Max Range: 7.7519. Min Range: -7.7519

Max Act: 7.0956. Min Act: -0.1700

Data Index: 1122182 (Open Web Text)

Max Activating Token Index: 272

Text #15

Max Range: 7.7519. Min Range: -7.7519

Max Act: 7.0644. Min Act: -0.1700

Data Index: 3382217 (Open Web Text)

Max Activating Token Index: 113

Text #16

Max Range: 7.7519. Min Range: -7.7519

Max Act: 7.0331. Min Act: -0.1700

Data Index: 1522359 (Open Web Text)

Max Activating Token Index: 513

Text #17

Max Range: 7.7519. Min Range: -7.7519

Max Act: 7.0019. Min Act: -0.1700

Data Index: 6084211 (Open Web Text)

Max Activating Token Index: 540

Text #18

Max Range: 7.7519. Min Range: -7.7519

Max Act: 7.0019. Min Act: -0.1700

Data Index: 4289064 (Open Web Text)

Max Activating Token Index: 827

Text #19

Max Range: 7.7519. Min Range: -7.7519

Max Act: 7.0019. Min Act: -0.1700

Data Index: 6542175 (Open Web Text)

Max Activating Token Index: 660