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

Dataset: Open Web Text

Neuron 688 in Layer 36

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: 7484492 (Open Web Text)

Max Activating Token Index: 393

Text #1

Max Range: 6.1016. Min Range: -6.1016

Max Act: 6.0079. Min Act: -0.1700

Data Index: 5477667 (Open Web Text)

Max Activating Token Index: 990

Text #2

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9766. Min Act: -0.1700

Data Index: 4917324 (Open Web Text)

Max Activating Token Index: 834

Text #3

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9766. Min Act: -0.1700

Data Index: 6596512 (Open Web Text)

Max Activating Token Index: 609

Text #4

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9766. Min Act: -0.1700

Data Index: 2494390 (Open Web Text)

Max Activating Token Index: 530

Text #5

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9766. Min Act: -0.1700

Data Index: 8624979 (Open Web Text)

Max Activating Token Index: 611

Text #6

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9766. Min Act: -0.1700

Data Index: 3920421 (Open Web Text)

Max Activating Token Index: 772

Text #7

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9766. Min Act: -0.1700

Data Index: 1241952 (Open Web Text)

Max Activating Token Index: 571

Text #8

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9141. Min Act: -0.1700

Data Index: 2140597 (Open Web Text)

Max Activating Token Index: 203

Text #9

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9141. Min Act: -0.1700

Data Index: 1812877 (Open Web Text)

Max Activating Token Index: 925

Text #10

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9141. Min Act: -0.1700

Data Index: 4398238 (Open Web Text)

Max Activating Token Index: 442

Text #11

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8829. Min Act: -0.1700

Data Index: 3706289 (Open Web Text)

Max Activating Token Index: 754

Text #12

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8829. Min Act: -0.1700

Data Index: 8489557 (Open Web Text)

Max Activating Token Index: 746

Text #13

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8829. Min Act: -0.1700

Data Index: 1659431 (Open Web Text)

Max Activating Token Index: 476

Text #14

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.9141. Min Act: -0.1700

Data Index: 6421115 (Open Web Text)

Max Activating Token Index: 738

Text #15

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8516. Min Act: -0.1700

Data Index: 3530481 (Open Web Text)

Max Activating Token Index: 750

Text #16

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8516. Min Act: -0.1700

Data Index: 8445956 (Open Web Text)

Max Activating Token Index: 784

Text #17

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8516. Min Act: -0.1700

Data Index: 1348999 (Open Web Text)

Max Activating Token Index: 424

Text #18

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8204. Min Act: -0.1700

Data Index: 6676961 (Open Web Text)

Max Activating Token Index: 97

Text #19

Max Range: 6.1016. Min Range: -6.1016

Max Act: 5.8204. Min Act: -0.1700

Data Index: 5913579 (Open Web Text)

Max Activating Token Index: 662