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

Dataset: Open Web Text

Neuron 4076 in Layer 18

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.8320. Min Act: -0.1700

Data Index: 8218371 (Open Web Text)

Max Activating Token Index: 638

Text #1

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.7695. Min Act: -0.1700

Data Index: 6421380 (Open Web Text)

Max Activating Token Index: 185

Text #2

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.7695. Min Act: -0.1700

Data Index: 2759046 (Open Web Text)

Max Activating Token Index: 174

Text #3

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.6445. Min Act: -0.1700

Data Index: 5562413 (Open Web Text)

Max Activating Token Index: 833

Text #4

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.5195. Min Act: -0.1700

Data Index: 1453916 (Open Web Text)

Max Activating Token Index: 859

Text #5

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.4883. Min Act: -0.1700

Data Index: 4755640 (Open Web Text)

Max Activating Token Index: 635

Text #6

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.4258. Min Act: -0.1700

Data Index: 2330851 (Open Web Text)

Max Activating Token Index: 320

Text #7

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.3633. Min Act: -0.1700

Data Index: 4747331 (Open Web Text)

Max Activating Token Index: 193

Text #8

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.3320. Min Act: -0.1700

Data Index: 1136364 (Open Web Text)

Max Activating Token Index: 153

Text #9

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.2695. Min Act: -0.1700

Data Index: 3157953 (Open Web Text)

Max Activating Token Index: 32

Text #10

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.3008. Min Act: -0.1700

Data Index: 7359216 (Open Web Text)

Max Activating Token Index: 415

Text #11

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.2695. Min Act: -0.1700

Data Index: 8392944 (Open Web Text)

Max Activating Token Index: 493

Text #12

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.2695. Min Act: -0.1700

Data Index: 1027921 (Open Web Text)

Max Activating Token Index: 63

Text #13

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.2695. Min Act: -0.1700

Data Index: 3618155 (Open Web Text)

Max Activating Token Index: 758

Text #14

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.2070. Min Act: -0.1700

Data Index: 5045882 (Open Web Text)

Max Activating Token Index: 786

Text #15

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.2383. Min Act: -0.1700

Data Index: 6125842 (Open Web Text)

Max Activating Token Index: 847

Text #16

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.2070. Min Act: -0.1700

Data Index: 3098507 (Open Web Text)

Max Activating Token Index: 402

Text #17

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.2070. Min Act: -0.1700

Data Index: 8094489 (Open Web Text)

Max Activating Token Index: 684

Text #18

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.2070. Min Act: -0.1700

Data Index: 5368855 (Open Web Text)

Max Activating Token Index: 848

Text #19

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.1758. Min Act: -0.1700

Data Index: 1831333 (Open Web Text)

Max Activating Token Index: 782