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

Dataset: Open Web Text

Neuron 3876 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6771. Min Act: -0.1698

Data Index: 2746282 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6423. Min Act: -0.1700

Data Index: 6944142 (Open Web Text)

Max Activating Token Index: 17

Text #2

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5900. Min Act: -0.1700

Data Index: 3120763 (Open Web Text)

Max Activating Token Index: 111

Text #3

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5812. Min Act: -0.1700

Data Index: 1577147 (Open Web Text)

Max Activating Token Index: 47

Text #4

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5812. Min Act: -0.1700

Data Index: 5407949 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5725. Min Act: -0.1696

Data Index: 390635 (Open Web Text)

Max Activating Token Index: 144

Text #6

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5812. Min Act: -0.1700

Data Index: 4325943 (Open Web Text)

Max Activating Token Index: 167

Text #7

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5812. Min Act: -0.1700

Data Index: 4038372 (Open Web Text)

Max Activating Token Index: 47

Text #8

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5725. Min Act: -0.1700

Data Index: 379639 (Open Web Text)

Max Activating Token Index: 156

Text #9

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5550. Min Act: -0.1697

Data Index: 168992 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5637. Min Act: -0.1700

Data Index: 5461345 (Open Web Text)

Max Activating Token Index: 53

Text #11

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5725. Min Act: -0.1698

Data Index: 379641 (Open Web Text)

Max Activating Token Index: 153

Text #12

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5725. Min Act: -0.1700

Data Index: 5594416 (Open Web Text)

Max Activating Token Index: 50

Text #13

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5725. Min Act: -0.1700

Data Index: 3670794 (Open Web Text)

Max Activating Token Index: 63

Text #14

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5725. Min Act: -0.1688

Data Index: 5518472 (Open Web Text)

Max Activating Token Index: 184

Text #15

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5550. Min Act: -0.1700

Data Index: 3670796 (Open Web Text)

Max Activating Token Index: 44

Text #16

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5550. Min Act: -0.1696

Data Index: 3476353 (Open Web Text)

Max Activating Token Index: 22

Text #17

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5637. Min Act: -0.1700

Data Index: 3999059 (Open Web Text)

Max Activating Token Index: 19

Text #18

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5637. Min Act: -0.1700

Data Index: 3024519 (Open Web Text)

Max Activating Token Index: 13

Text #19

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5550. Min Act: -0.1688

Data Index: 58110 (Open Web Text)

Max Activating Token Index: 40