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

Dataset: Open Web Text

Neuron 5607 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1016. Min Range: -5.1016

Max Act: 5.1016. Min Act: -0.1700

Data Index: 2869028 (Open Web Text)

Max Activating Token Index: 167

Text #1

Max Range: 5.1016. Min Range: -5.1016

Max Act: 5.1016. Min Act: -0.1700

Data Index: 4302872 (Open Web Text)

Max Activating Token Index: 836

Text #2

Max Range: 5.1016. Min Range: -5.1016

Max Act: 5.1016. Min Act: -0.1700

Data Index: 674408 (Open Web Text)

Max Activating Token Index: 883

Text #3

Max Range: 5.1016. Min Range: -5.1016

Max Act: 5.0704. Min Act: -0.1700

Data Index: 5469374 (Open Web Text)

Max Activating Token Index: 914

Text #4

Max Range: 5.1016. Min Range: -5.1016

Max Act: 5.0391. Min Act: -0.1700

Data Index: 4894815 (Open Web Text)

Max Activating Token Index: 688

Text #5

Max Range: 5.1016. Min Range: -5.1016

Max Act: 5.0391. Min Act: -0.1700

Data Index: 3170049 (Open Web Text)

Max Activating Token Index: 417

Text #6

Max Range: 5.1016. Min Range: -5.1016

Max Act: 5.0391. Min Act: -0.1700

Data Index: 5867277 (Open Web Text)

Max Activating Token Index: 347

Text #7

Max Range: 5.1016. Min Range: -5.1016

Max Act: 5.0079. Min Act: -0.1700

Data Index: 3488197 (Open Web Text)

Max Activating Token Index: 689

Text #8

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.9766. Min Act: -0.1700

Data Index: 4488452 (Open Web Text)

Max Activating Token Index: 395

Text #9

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.9454. Min Act: -0.1700

Data Index: 6262761 (Open Web Text)

Max Activating Token Index: 955

Text #10

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.9141. Min Act: -0.1700

Data Index: 1584238 (Open Web Text)

Max Activating Token Index: 146

Text #11

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.9141. Min Act: -0.1700

Data Index: 6911221 (Open Web Text)

Max Activating Token Index: 716

Text #12

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.9141. Min Act: -0.1700

Data Index: 6812384 (Open Web Text)

Max Activating Token Index: 267

Text #13

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.9141. Min Act: -0.1700

Data Index: 2650151 (Open Web Text)

Max Activating Token Index: 160

Text #14

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.9141. Min Act: -0.1700

Data Index: 8678496 (Open Web Text)

Max Activating Token Index: 532

Text #15

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.9141. Min Act: -0.1700

Data Index: 8429956 (Open Web Text)

Max Activating Token Index: 465

Text #16

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.9141. Min Act: -0.1700

Data Index: 2130710 (Open Web Text)

Max Activating Token Index: 314

Text #17

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.9141. Min Act: -0.1700

Data Index: 809300 (Open Web Text)

Max Activating Token Index: 461

Text #18

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.8829. Min Act: -0.1700

Data Index: 5630291 (Open Web Text)

Max Activating Token Index: 836

Text #19

Max Range: 5.1016. Min Range: -5.1016

Max Act: 4.8829. Min Act: -0.1700

Data Index: 5755176 (Open Web Text)

Max Activating Token Index: 795