Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 4352 in Layer 29

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.6771. Min Range: -7.6771

Max Act: 7.6771. Min Act: -0.1700

Data Index: 7217792 (Open Web Text)

Max Activating Token Index: 234

Text #1

Max Range: 7.6771. Min Range: -7.6771

Max Act: 7.4896. Min Act: -0.1700

Data Index: 7709446 (Open Web Text)

Max Activating Token Index: 480

Text #2

Max Range: 7.6771. Min Range: -7.6771

Max Act: 7.3646. Min Act: -0.1700

Data Index: 3794831 (Open Web Text)

Max Activating Token Index: 598

Text #3

Max Range: 7.6771. Min Range: -7.6771

Max Act: 7.3334. Min Act: -0.1700

Data Index: 6999906 (Open Web Text)

Max Activating Token Index: 245

Text #4

Max Range: 7.6771. Min Range: -7.6771

Max Act: 7.1459. Min Act: -0.1700

Data Index: 6604235 (Open Web Text)

Max Activating Token Index: 20

Text #5

Max Range: 7.6771. Min Range: -7.6771

Max Act: 7.1146. Min Act: -0.1700

Data Index: 3119907 (Open Web Text)

Max Activating Token Index: 543

Text #6

Max Range: 7.6771. Min Range: -7.6771

Max Act: 7.0521. Min Act: -0.1700

Data Index: 4520681 (Open Web Text)

Max Activating Token Index: 44

Text #7

Max Range: 7.6771. Min Range: -7.6771

Max Act: 7.0209. Min Act: -0.1700

Data Index: 3128970 (Open Web Text)

Max Activating Token Index: 73

Text #8

Max Range: 7.6771. Min Range: -7.6771

Max Act: 6.9896. Min Act: -0.1700

Data Index: 2037915 (Open Web Text)

Max Activating Token Index: 586

Text #9

Max Range: 7.6771. Min Range: -7.6771

Max Act: 6.9584. Min Act: -0.1700

Data Index: 6017330 (Open Web Text)

Max Activating Token Index: 989

Text #10

Max Range: 7.6771. Min Range: -7.6771

Max Act: 6.9271. Min Act: -0.1700

Data Index: 2048752 (Open Web Text)

Max Activating Token Index: 298

Text #11

Max Range: 7.6771. Min Range: -7.6771

Max Act: 6.8959. Min Act: -0.1700

Data Index: 8815759 (Open Web Text)

Max Activating Token Index: 846

Text #12

Max Range: 7.6771. Min Range: -7.6771

Max Act: 6.8646. Min Act: -0.1700

Data Index: 1040218 (Open Web Text)

Max Activating Token Index: 273

Text #13

Max Range: 7.6771. Min Range: -7.6771

Max Act: 6.8021. Min Act: -0.1700

Data Index: 6957519 (Open Web Text)

Max Activating Token Index: 617

Text #14

Max Range: 7.6771. Min Range: -7.6771

Max Act: 6.8021. Min Act: -0.1700

Data Index: 1205520 (Open Web Text)

Max Activating Token Index: 291

Text #15

Max Range: 7.6771. Min Range: -7.6771

Max Act: 6.7709. Min Act: -0.1700

Data Index: 4827826 (Open Web Text)

Max Activating Token Index: 34

Text #16

Max Range: 7.6771. Min Range: -7.6771

Max Act: 6.7709. Min Act: -0.1700

Data Index: 7789801 (Open Web Text)

Max Activating Token Index: 943

Text #17

Max Range: 7.6771. Min Range: -7.6771

Max Act: 6.7709. Min Act: -0.1700

Data Index: 495324 (Open Web Text)

Max Activating Token Index: 417

Text #18

Max Range: 7.6771. Min Range: -7.6771

Max Act: 6.7396. Min Act: -0.1700

Data Index: 2632993 (Open Web Text)

Max Activating Token Index: 507

Text #19

Max Range: 7.6771. Min Range: -7.6771

Max Act: 6.7084. Min Act: -0.1700

Data Index: 4147425 (Open Web Text)

Max Activating Token Index: 191