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

Dataset: Open Web Text

Neuron 2778 in Layer 0

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: 2.8540. Min Range: -2.8540

Max Act: 2.8540. Min Act: -0.1700

Data Index: 8527086 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.8540. Min Range: -2.8540

Max Act: 2.8198. Min Act: -0.1700

Data Index: 1590804 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 2.8540. Min Range: -2.8540

Max Act: 2.7688. Min Act: -0.1700

Data Index: 7647925 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.8540. Min Range: -2.8540

Max Act: 2.7664. Min Act: -0.1700

Data Index: 5383663 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.8540. Min Range: -2.8540

Max Act: 2.7611. Min Act: -0.1700

Data Index: 4611405 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.8540. Min Range: -2.8540

Max Act: 2.7693. Min Act: -0.1700

Data Index: 3369603 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.8540. Min Range: -2.8540

Max Act: 2.7443. Min Act: -0.1700

Data Index: 8539070 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.8540. Min Range: -2.8540

Max Act: 2.7396. Min Act: -0.1700

Data Index: 2287293 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.8540. Min Range: -2.8540

Max Act: 2.7583. Min Act: -0.1700

Data Index: 3875988 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 2.8540. Min Range: -2.8540

Max Act: 2.7361. Min Act: -0.1700

Data Index: 8385974 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.8540. Min Range: -2.8540

Max Act: 2.7422. Min Act: -0.1700

Data Index: 8362084 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.8540. Min Range: -2.8540

Max Act: 2.7432. Min Act: -0.1700

Data Index: 7693943 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.8540. Min Range: -2.8540

Max Act: 2.7376. Min Act: -0.1700

Data Index: 7068634 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.8540. Min Range: -2.8540

Max Act: 2.7382. Min Act: -0.1700

Data Index: 4245234 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 2.8540. Min Range: -2.8540

Max Act: 2.7323. Min Act: -0.1700

Data Index: 7481750 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.8540. Min Range: -2.8540

Max Act: 2.7371. Min Act: -0.1700

Data Index: 5700800 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.8540. Min Range: -2.8540

Max Act: 2.7367. Min Act: -0.1700

Data Index: 3947520 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.8540. Min Range: -2.8540

Max Act: 2.7280. Min Act: -0.1700

Data Index: 6973585 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.8540. Min Range: -2.8540

Max Act: 2.7192. Min Act: -0.1700

Data Index: 7252636 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.8540. Min Range: -2.8540

Max Act: 2.7208. Min Act: -0.1700

Data Index: 604785 (Open Web Text)

Max Activating Token Index: 4