Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 2340 in Layer 23

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7571. Min Range: -7.7571

Max Act: 7.1634. Min Act: -0.1700

Data Index: 3988404 (Open Web Text)

Max Activating Token Index: 144

Text #1

Max Range: 7.7571. Min Range: -7.7571

Max Act: 7.7571. Min Act: -0.1700

Data Index: 6562139 (Open Web Text)

Max Activating Token Index: 785

Text #2

Max Range: 7.7571. Min Range: -7.7571

Max Act: 7.5696. Min Act: -0.1700

Data Index: 3226910 (Open Web Text)

Max Activating Token Index: 796

Text #3

Max Range: 7.7571. Min Range: -7.7571

Max Act: 6.9134. Min Act: -0.1700

Data Index: 5620034 (Open Web Text)

Max Activating Token Index: 27

Text #4

Max Range: 7.7571. Min Range: -7.7571

Max Act: 7.1634. Min Act: -0.1698

Data Index: 6606555 (Open Web Text)

Max Activating Token Index: 934

Text #5

Max Range: 7.7571. Min Range: -7.7571

Max Act: 4.7259. Min Act: -0.1699

Data Index: 4237261 (Open Web Text)

Max Activating Token Index: 534

Text #6

Max Range: 7.7571. Min Range: -7.7571

Max Act: 7.2259. Min Act: -0.1700

Data Index: 1199284 (Open Web Text)

Max Activating Token Index: 319

Text #7

Max Range: 7.7571. Min Range: -7.7571

Max Act: 5.7571. Min Act: -0.1700

Data Index: 5717107 (Open Web Text)

Max Activating Token Index: 1009

Text #8

Max Range: 7.7571. Min Range: -7.7571

Max Act: 4.4134. Min Act: -0.1700

Data Index: 552234 (Open Web Text)

Max Activating Token Index: 296

Text #9

Max Range: 7.7571. Min Range: -7.7571

Max Act: 6.8196. Min Act: -0.1700

Data Index: 7999004 (Open Web Text)

Max Activating Token Index: 340

Text #10

Max Range: 7.7571. Min Range: -7.7571

Max Act: 6.6634. Min Act: -0.1700

Data Index: 971093 (Open Web Text)

Max Activating Token Index: 403

Text #11

Max Range: 7.7571. Min Range: -7.7571

Max Act: 6.8821. Min Act: -0.1700

Data Index: 8521299 (Open Web Text)

Max Activating Token Index: 501

Text #12

Max Range: 7.7571. Min Range: -7.7571

Max Act: 6.9759. Min Act: -0.1700

Data Index: 1561260 (Open Web Text)

Max Activating Token Index: 92

Text #13

Max Range: 7.7571. Min Range: -7.7571

Max Act: 6.3821. Min Act: -0.1700

Data Index: 3775708 (Open Web Text)

Max Activating Token Index: 232

Text #14

Max Range: 7.7571. Min Range: -7.7571

Max Act: 6.7884. Min Act: -0.1700

Data Index: 5825016 (Open Web Text)

Max Activating Token Index: 874

Text #15

Max Range: 7.7571. Min Range: -7.7571

Max Act: 5.1946. Min Act: -0.1700

Data Index: 6295211 (Open Web Text)

Max Activating Token Index: 378

Text #16

Max Range: 7.7571. Min Range: -7.7571

Max Act: 5.5071. Min Act: -0.1699

Data Index: 1901588 (Open Web Text)

Max Activating Token Index: 667

Text #17

Max Range: 7.7571. Min Range: -7.7571

Max Act: 6.2259. Min Act: -0.1700

Data Index: 7514963 (Open Web Text)

Max Activating Token Index: 658

Text #18

Max Range: 7.7571. Min Range: -7.7571

Max Act: 4.5384. Min Act: -0.1700

Data Index: 4344464 (Open Web Text)

Max Activating Token Index: 527

Text #19

Max Range: 7.7571. Min Range: -7.7571

Max Act: 5.6321. Min Act: -0.1700

Data Index: 6234533 (Open Web Text)

Max Activating Token Index: 549