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

Dataset: Open Web Text

Neuron 2707 in Layer 4

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: 3.1507. Min Range: -3.1507

Max Act: 3.1507. Min Act: -0.1700

Data Index: 4256823 (Open Web Text)

Max Activating Token Index: 859

Text #1

Max Range: 3.1507. Min Range: -3.1507

Max Act: 3.1466. Min Act: -0.1700

Data Index: 2066704 (Open Web Text)

Max Activating Token Index: 225

Text #2

Max Range: 3.1507. Min Range: -3.1507

Max Act: 3.1343. Min Act: -0.1700

Data Index: 3308170 (Open Web Text)

Max Activating Token Index: 934

Text #3

Max Range: 3.1507. Min Range: -3.1507

Max Act: 3.1115. Min Act: -0.1700

Data Index: 1333450 (Open Web Text)

Max Activating Token Index: 196

Text #4

Max Range: 3.1507. Min Range: -3.1507

Max Act: 3.1133. Min Act: -0.1700

Data Index: 7827210 (Open Web Text)

Max Activating Token Index: 627

Text #5

Max Range: 3.1507. Min Range: -3.1507

Max Act: 3.1216. Min Act: -0.1700

Data Index: 7083668 (Open Web Text)

Max Activating Token Index: 553

Text #6

Max Range: 3.1507. Min Range: -3.1507

Max Act: 3.1073. Min Act: -0.1700

Data Index: 3172809 (Open Web Text)

Max Activating Token Index: 967

Text #7

Max Range: 3.1507. Min Range: -3.1507

Max Act: 3.0963. Min Act: -0.1700

Data Index: 4395581 (Open Web Text)

Max Activating Token Index: 242

Text #8

Max Range: 3.1507. Min Range: -3.1507

Max Act: 3.0998. Min Act: -0.1700

Data Index: 4487200 (Open Web Text)

Max Activating Token Index: 299

Text #9

Max Range: 3.1507. Min Range: -3.1507

Max Act: 3.0949. Min Act: -0.1700

Data Index: 6438312 (Open Web Text)

Max Activating Token Index: 714

Text #10

Max Range: 3.1507. Min Range: -3.1507

Max Act: 3.0839. Min Act: -0.1700

Data Index: 8377498 (Open Web Text)

Max Activating Token Index: 709

Text #11

Max Range: 3.1507. Min Range: -3.1507

Max Act: 3.0997. Min Act: -0.1700

Data Index: 7932573 (Open Web Text)

Max Activating Token Index: 915

Text #12

Max Range: 3.1507. Min Range: -3.1507

Max Act: 3.1029. Min Act: -0.1700

Data Index: 8001540 (Open Web Text)

Max Activating Token Index: 90

Text #13

Max Range: 3.1507. Min Range: -3.1507

Max Act: 3.0927. Min Act: -0.1700

Data Index: 8247492 (Open Web Text)

Max Activating Token Index: 36

Text #14

Max Range: 3.1507. Min Range: -3.1507

Max Act: 3.0812. Min Act: -0.1700

Data Index: 4351652 (Open Web Text)

Max Activating Token Index: 755

Text #15

Max Range: 3.1507. Min Range: -3.1507

Max Act: 3.0697. Min Act: -0.1700

Data Index: 7172446 (Open Web Text)

Max Activating Token Index: 791

Text #16

Max Range: 3.1507. Min Range: -3.1507

Max Act: 3.0903. Min Act: -0.1700

Data Index: 5945497 (Open Web Text)

Max Activating Token Index: 550

Text #17

Max Range: 3.1507. Min Range: -3.1507

Max Act: 3.0857. Min Act: -0.1700

Data Index: 6265951 (Open Web Text)

Max Activating Token Index: 518

Text #18

Max Range: 3.1507. Min Range: -3.1507

Max Act: 3.0804. Min Act: -0.1700

Data Index: 2233364 (Open Web Text)

Max Activating Token Index: 942

Text #19

Max Range: 3.1507. Min Range: -3.1507

Max Act: 3.0626. Min Act: -0.1700

Data Index: 3910052 (Open Web Text)

Max Activating Token Index: 1001