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

Dataset: Open Web Text

Neuron 1885 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: 2.1511. Min Range: -2.1511

Max Act: 2.1511. Min Act: -0.1700

Data Index: 2139895 (Open Web Text)

Max Activating Token Index: 174

Text #1

Max Range: 2.1511. Min Range: -2.1511

Max Act: 2.0838. Min Act: -0.1700

Data Index: 8357950 (Open Web Text)

Max Activating Token Index: 872

Text #2

Max Range: 2.1511. Min Range: -2.1511

Max Act: 2.0594. Min Act: -0.1700

Data Index: 6346561 (Open Web Text)

Max Activating Token Index: 726

Text #3

Max Range: 2.1511. Min Range: -2.1511

Max Act: 2.0350. Min Act: -0.1700

Data Index: 1374609 (Open Web Text)

Max Activating Token Index: 768

Text #4

Max Range: 2.1511. Min Range: -2.1511

Max Act: 2.0227. Min Act: -0.1700

Data Index: 7994590 (Open Web Text)

Max Activating Token Index: 813

Text #5

Max Range: 2.1511. Min Range: -2.1511

Max Act: 2.0328. Min Act: -0.1700

Data Index: 4957597 (Open Web Text)

Max Activating Token Index: 104

Text #6

Max Range: 2.1511. Min Range: -2.1511

Max Act: 1.9787. Min Act: -0.1700

Data Index: 7543010 (Open Web Text)

Max Activating Token Index: 446

Text #7

Max Range: 2.1511. Min Range: -2.1511

Max Act: 1.9732. Min Act: -0.1700

Data Index: 3218392 (Open Web Text)

Max Activating Token Index: 40

Text #8

Max Range: 2.1511. Min Range: -2.1511

Max Act: 1.9740. Min Act: -0.1700

Data Index: 3594419 (Open Web Text)

Max Activating Token Index: 38

Text #9

Max Range: 2.1511. Min Range: -2.1511

Max Act: 1.9499. Min Act: -0.1700

Data Index: 3967382 (Open Web Text)

Max Activating Token Index: 25

Text #10

Max Range: 2.1511. Min Range: -2.1511

Max Act: 1.9410. Min Act: -0.1700

Data Index: 4996767 (Open Web Text)

Max Activating Token Index: 66

Text #11

Max Range: 2.1511. Min Range: -2.1511

Max Act: 1.9589. Min Act: -0.1700

Data Index: 1398417 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 2.1511. Min Range: -2.1511

Max Act: 1.9469. Min Act: -0.1700

Data Index: 124338 (Open Web Text)

Max Activating Token Index: 594

Text #13

Max Range: 2.1511. Min Range: -2.1511

Max Act: 1.9532. Min Act: -0.1700

Data Index: 7080102 (Open Web Text)

Max Activating Token Index: 288

Text #14

Max Range: 2.1511. Min Range: -2.1511

Max Act: 1.9446. Min Act: -0.1700

Data Index: 6066709 (Open Web Text)

Max Activating Token Index: 763

Text #15

Max Range: 2.1511. Min Range: -2.1511

Max Act: 1.9427. Min Act: -0.1700

Data Index: 1725467 (Open Web Text)

Max Activating Token Index: 39

Text #16

Max Range: 2.1511. Min Range: -2.1511

Max Act: 1.9504. Min Act: -0.1700

Data Index: 1610684 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 2.1511. Min Range: -2.1511

Max Act: 1.9559. Min Act: -0.1700

Data Index: 5041866 (Open Web Text)

Max Activating Token Index: 525

Text #18

Max Range: 2.1511. Min Range: -2.1511

Max Act: 1.9416. Min Act: -0.1700

Data Index: 7837378 (Open Web Text)

Max Activating Token Index: 657

Text #19

Max Range: 2.1511. Min Range: -2.1511

Max Act: 1.9245. Min Act: -0.1700

Data Index: 7063334 (Open Web Text)

Max Activating Token Index: 182