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

Dataset: Open Web Text

Neuron 3771 in Layer 1

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: 5638129 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9453. Min Act: -0.1700

Data Index: 5095521 (Open Web Text)

Max Activating Token Index: 585

Text #2

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9453. Min Act: -0.1700

Data Index: 8756321 (Open Web Text)

Max Activating Token Index: 1019

Text #3

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9453. Min Act: -0.1700

Data Index: 173732 (Open Web Text)

Max Activating Token Index: 165

Text #4

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9141. Min Act: -0.1700

Data Index: 1847592 (Open Web Text)

Max Activating Token Index: 469

Text #5

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9141. Min Act: -0.1700

Data Index: 5031213 (Open Web Text)

Max Activating Token Index: 369

Text #6

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9141. Min Act: -0.1700

Data Index: 7454791 (Open Web Text)

Max Activating Token Index: 579

Text #7

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8828. Min Act: -0.1700

Data Index: 5516828 (Open Web Text)

Max Activating Token Index: 529

Text #8

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8828. Min Act: -0.1700

Data Index: 8364627 (Open Web Text)

Max Activating Token Index: 459

Text #9

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8828. Min Act: -0.1700

Data Index: 7813032 (Open Web Text)

Max Activating Token Index: 970

Text #10

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8828. Min Act: -0.1700

Data Index: 2582592 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8828. Min Act: -0.1700

Data Index: 5238159 (Open Web Text)

Max Activating Token Index: 634

Text #12

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8828. Min Act: -0.1700

Data Index: 8806234 (Open Web Text)

Max Activating Token Index: 265

Text #13

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8828. Min Act: -0.1700

Data Index: 8756322 (Open Web Text)

Max Activating Token Index: 70

Text #14

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8828. Min Act: -0.1700

Data Index: 4919913 (Open Web Text)

Max Activating Token Index: 520

Text #15

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8516. Min Act: -0.1700

Data Index: 5327149 (Open Web Text)

Max Activating Token Index: 747

Text #16

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8516. Min Act: -0.1700

Data Index: 1971789 (Open Web Text)

Max Activating Token Index: 236

Text #17

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8516. Min Act: -0.1700

Data Index: 2531872 (Open Web Text)

Max Activating Token Index: 879

Text #18

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8516. Min Act: -0.1700

Data Index: 6969244 (Open Web Text)

Max Activating Token Index: 88

Text #19

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8516. Min Act: -0.1700

Data Index: 4909064 (Open Web Text)

Max Activating Token Index: 541