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

Dataset: Open Web Text

Neuron 669 in Layer 35

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.1016. Min Range: -8.1016

Max Act: 8.1016. Min Act: -0.1700

Data Index: 1628778 (Open Web Text)

Max Activating Token Index: 731

Text #1

Max Range: 8.1016. Min Range: -8.1016

Max Act: 8.0391. Min Act: -0.1700

Data Index: 7700086 (Open Web Text)

Max Activating Token Index: 696

Text #2

Max Range: 8.1016. Min Range: -8.1016

Max Act: 7.9141. Min Act: -0.1700

Data Index: 3477631 (Open Web Text)

Max Activating Token Index: 940

Text #3

Max Range: 8.1016. Min Range: -8.1016

Max Act: 7.7266. Min Act: -0.1700

Data Index: 125642 (Open Web Text)

Max Activating Token Index: 915

Text #4

Max Range: 8.1016. Min Range: -8.1016

Max Act: 7.8516. Min Act: -0.1700

Data Index: 7423862 (Open Web Text)

Max Activating Token Index: 672

Text #5

Max Range: 8.1016. Min Range: -8.1016

Max Act: 7.7266. Min Act: -0.1700

Data Index: 3972923 (Open Web Text)

Max Activating Token Index: 190

Text #6

Max Range: 8.1016. Min Range: -8.1016

Max Act: 7.7266. Min Act: -0.1700

Data Index: 5738724 (Open Web Text)

Max Activating Token Index: 287

Text #7

Max Range: 8.1016. Min Range: -8.1016

Max Act: 7.7266. Min Act: -0.1700

Data Index: 7289807 (Open Web Text)

Max Activating Token Index: 277

Text #8

Max Range: 8.1016. Min Range: -8.1016

Max Act: 7.6641. Min Act: -0.1700

Data Index: 7588882 (Open Web Text)

Max Activating Token Index: 280

Text #9

Max Range: 8.1016. Min Range: -8.1016

Max Act: 7.6016. Min Act: -0.1700

Data Index: 8217265 (Open Web Text)

Max Activating Token Index: 877

Text #10

Max Range: 8.1016. Min Range: -8.1016

Max Act: 7.6641. Min Act: -0.1700

Data Index: 2426970 (Open Web Text)

Max Activating Token Index: 811

Text #11

Max Range: 8.1016. Min Range: -8.1016

Max Act: 7.5391. Min Act: -0.1700

Data Index: 7397921 (Open Web Text)

Max Activating Token Index: 637

Text #12

Max Range: 8.1016. Min Range: -8.1016

Max Act: 7.5391. Min Act: -0.1700

Data Index: 8570035 (Open Web Text)

Max Activating Token Index: 528

Text #13

Max Range: 8.1016. Min Range: -8.1016

Max Act: 7.5391. Min Act: -0.1700

Data Index: 722732 (Open Web Text)

Max Activating Token Index: 279

Text #14

Max Range: 8.1016. Min Range: -8.1016

Max Act: 7.5391. Min Act: -0.1700

Data Index: 7950086 (Open Web Text)

Max Activating Token Index: 288

Text #15

Max Range: 8.1016. Min Range: -8.1016

Max Act: 7.5391. Min Act: -0.1700

Data Index: 978162 (Open Web Text)

Max Activating Token Index: 941

Text #16

Max Range: 8.1016. Min Range: -8.1016

Max Act: 7.5391. Min Act: -0.1700

Data Index: 8015379 (Open Web Text)

Max Activating Token Index: 328

Text #17

Max Range: 8.1016. Min Range: -8.1016

Max Act: 7.5391. Min Act: -0.1700

Data Index: 6463479 (Open Web Text)

Max Activating Token Index: 416

Text #18

Max Range: 8.1016. Min Range: -8.1016

Max Act: 7.4766. Min Act: -0.1700

Data Index: 6170004 (Open Web Text)

Max Activating Token Index: 823

Text #19

Max Range: 8.1016. Min Range: -8.1016

Max Act: 7.4766. Min Act: -0.1700

Data Index: 2096000 (Open Web Text)

Max Activating Token Index: 386