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

Dataset: Open Web Text

Neuron 1343 in Layer 29

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1016. Min Range: -6.1016

Max Act: 6.1016. Min Act: -0.1700

Data Index: 2485682 (Open Web Text)

Max Activating Token Index: 1013

Text #1

Max Range: 6.1016. Min Range: -6.1016

Max Act: 6.0079. Min Act: -0.1700

Data Index: 5747212 (Open Web Text)

Max Activating Token Index: 882

Text #2

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9454. Min Act: -0.1700

Data Index: 5135952 (Open Web Text)

Max Activating Token Index: 794

Text #3

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9766. Min Act: -0.1700

Data Index: 8149128 (Open Web Text)

Max Activating Token Index: 600

Text #4

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9766. Min Act: -0.1700

Data Index: 2922802 (Open Web Text)

Max Activating Token Index: 882

Text #5

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9454. Min Act: -0.1700

Data Index: 4493284 (Open Web Text)

Max Activating Token Index: 446

Text #6

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8829. Min Act: -0.1700

Data Index: 8724395 (Open Web Text)

Max Activating Token Index: 236

Text #7

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8516. Min Act: -0.1700

Data Index: 390673 (Open Web Text)

Max Activating Token Index: 821

Text #8

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.7891. Min Act: -0.1700

Data Index: 4663123 (Open Web Text)

Max Activating Token Index: 194

Text #9

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.7891. Min Act: -0.1700

Data Index: 3287604 (Open Web Text)

Max Activating Token Index: 778

Text #10

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.7579. Min Act: -0.1700

Data Index: 2250957 (Open Web Text)

Max Activating Token Index: 574

Text #11

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.7579. Min Act: -0.1700

Data Index: 8248001 (Open Web Text)

Max Activating Token Index: 186

Text #12

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.7266. Min Act: -0.1700

Data Index: 5275462 (Open Web Text)

Max Activating Token Index: 875

Text #13

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.7266. Min Act: -0.1700

Data Index: 4123754 (Open Web Text)

Max Activating Token Index: 852

Text #14

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.7579. Min Act: -0.1700

Data Index: 3110242 (Open Web Text)

Max Activating Token Index: 755

Text #15

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.6954. Min Act: -0.1700

Data Index: 2817598 (Open Web Text)

Max Activating Token Index: 643

Text #16

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.6954. Min Act: -0.1700

Data Index: 6699699 (Open Web Text)

Max Activating Token Index: 616

Text #17

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.6641. Min Act: -0.1700

Data Index: 5474404 (Open Web Text)

Max Activating Token Index: 235

Text #18

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.6641. Min Act: -0.1700

Data Index: 2295016 (Open Web Text)

Max Activating Token Index: 609

Text #19

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.6641. Min Act: -0.1700

Data Index: 8211703 (Open Web Text)

Max Activating Token Index: 538