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

Dataset: Open Web Text

Neuron 1613 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: 2.9498. Min Range: -2.9498

Max Act: 2.9498. Min Act: -0.1700

Data Index: 2466462 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 2.9498. Min Range: -2.9498

Max Act: 2.8620. Min Act: -0.1700

Data Index: 8475180 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 2.9498. Min Range: -2.9498

Max Act: 2.8387. Min Act: -0.1700

Data Index: 7676480 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 2.9498. Min Range: -2.9498

Max Act: 2.8527. Min Act: -0.1700

Data Index: 7476272 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.9498. Min Range: -2.9498

Max Act: 2.8433. Min Act: -0.1700

Data Index: 3354142 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.9498. Min Range: -2.9498

Max Act: 2.8417. Min Act: -0.1700

Data Index: 6751937 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.9498. Min Range: -2.9498

Max Act: 2.8402. Min Act: -0.1700

Data Index: 1745049 (Open Web Text)

Max Activating Token Index: 715

Text #7

Max Range: 2.9498. Min Range: -2.9498

Max Act: 2.8245. Min Act: -0.1700

Data Index: 2149200 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.9498. Min Range: -2.9498

Max Act: 2.8265. Min Act: -0.1700

Data Index: 2207032 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.9498. Min Range: -2.9498

Max Act: 2.8332. Min Act: -0.1700

Data Index: 7309524 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.9498. Min Range: -2.9498

Max Act: 2.8230. Min Act: -0.1700

Data Index: 1067384 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.9498. Min Range: -2.9498

Max Act: 2.8299. Min Act: -0.1700

Data Index: 6053517 (Open Web Text)

Max Activating Token Index: 657

Text #12

Max Range: 2.9498. Min Range: -2.9498

Max Act: 2.8239. Min Act: -0.1700

Data Index: 2016916 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.9498. Min Range: -2.9498

Max Act: 2.8093. Min Act: -0.1700

Data Index: 492861 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 2.9498. Min Range: -2.9498

Max Act: 2.8117. Min Act: -0.1700

Data Index: 5411067 (Open Web Text)

Max Activating Token Index: 634

Text #15

Max Range: 2.9498. Min Range: -2.9498

Max Act: 2.8138. Min Act: -0.1700

Data Index: 1786482 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 2.9498. Min Range: -2.9498

Max Act: 2.7970. Min Act: -0.1700

Data Index: 655578 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 2.9498. Min Range: -2.9498

Max Act: 2.7919. Min Act: -0.1700

Data Index: 5802151 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.9498. Min Range: -2.9498

Max Act: 2.8053. Min Act: -0.1700

Data Index: 4955876 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.9498. Min Range: -2.9498

Max Act: 2.7960. Min Act: -0.1700

Data Index: 4935389 (Open Web Text)

Max Activating Token Index: 717