Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 828 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 5.9084. Min Range: -5.9084

Max Act: 5.9084. Min Act: -0.1700

Data Index: 4512550 (Open Web Text)

Max Activating Token Index: 800

Text #1

Max Range: 5.9084. Min Range: -5.9084

Max Act: 5.4825. Min Act: -0.1700

Data Index: 5737046 (Open Web Text)

Max Activating Token Index: 507

Text #2

Max Range: 5.9084. Min Range: -5.9084

Max Act: 5.4928. Min Act: -0.1700

Data Index: 4404250 (Open Web Text)

Max Activating Token Index: 648

Text #3

Max Range: 5.9084. Min Range: -5.9084

Max Act: 5.4250. Min Act: -0.1700

Data Index: 4269451 (Open Web Text)

Max Activating Token Index: 431

Text #4

Max Range: 5.9084. Min Range: -5.9084

Max Act: 5.3501. Min Act: -0.1700

Data Index: 8007527 (Open Web Text)

Max Activating Token Index: 450

Text #5

Max Range: 5.9084. Min Range: -5.9084

Max Act: 5.5068. Min Act: -0.1700

Data Index: 2332707 (Open Web Text)

Max Activating Token Index: 612

Text #6

Max Range: 5.9084. Min Range: -5.9084

Max Act: 5.3607. Min Act: -0.1700

Data Index: 3930292 (Open Web Text)

Max Activating Token Index: 987

Text #7

Max Range: 5.9084. Min Range: -5.9084

Max Act: 5.3408. Min Act: -0.1700

Data Index: 6058697 (Open Web Text)

Max Activating Token Index: 808

Text #8

Max Range: 5.9084. Min Range: -5.9084

Max Act: 5.2869. Min Act: -0.1700

Data Index: 1070797 (Open Web Text)

Max Activating Token Index: 531

Text #9

Max Range: 5.9084. Min Range: -5.9084

Max Act: 5.2363. Min Act: -0.1700

Data Index: 8187687 (Open Web Text)

Max Activating Token Index: 492

Text #10

Max Range: 5.9084. Min Range: -5.9084

Max Act: 5.2014. Min Act: -0.1700

Data Index: 1347982 (Open Web Text)

Max Activating Token Index: 249

Text #11

Max Range: 5.9084. Min Range: -5.9084

Max Act: 5.2069. Min Act: -0.1700

Data Index: 8741478 (Open Web Text)

Max Activating Token Index: 624

Text #12

Max Range: 5.9084. Min Range: -5.9084

Max Act: 5.1747. Min Act: -0.1700

Data Index: 4954248 (Open Web Text)

Max Activating Token Index: 965

Text #13

Max Range: 5.9084. Min Range: -5.9084

Max Act: 5.1426. Min Act: -0.1700

Data Index: 5039535 (Open Web Text)

Max Activating Token Index: 819

Text #14

Max Range: 5.9084. Min Range: -5.9084

Max Act: 5.1689. Min Act: -0.1700

Data Index: 1803470 (Open Web Text)

Max Activating Token Index: 535

Text #15

Max Range: 5.9084. Min Range: -5.9084

Max Act: 5.1158. Min Act: -0.1700

Data Index: 4413319 (Open Web Text)

Max Activating Token Index: 153

Text #16

Max Range: 5.9084. Min Range: -5.9084

Max Act: 5.1016. Min Act: -0.1700

Data Index: 25389 (Open Web Text)

Max Activating Token Index: 937

Text #17

Max Range: 5.9084. Min Range: -5.9084

Max Act: 5.1377. Min Act: -0.1700

Data Index: 6711797 (Open Web Text)

Max Activating Token Index: 254

Text #18

Max Range: 5.9084. Min Range: -5.9084

Max Act: 5.1320. Min Act: -0.1700

Data Index: 4232748 (Open Web Text)

Max Activating Token Index: 200

Text #19

Max Range: 5.9084. Min Range: -5.9084

Max Act: 5.1111. Min Act: -0.1700

Data Index: 3053852 (Open Web Text)

Max Activating Token Index: 703