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

Dataset: Open Web Text

Neuron 39 in Layer 3

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: 3.3812. Min Range: -3.3812

Max Act: 3.3715. Min Act: -0.1700

Data Index: 3983491 (Open Web Text)

Max Activating Token Index: 679

Text #1

Max Range: 3.3812. Min Range: -3.3812

Max Act: 3.3804. Min Act: -0.1700

Data Index: 4120480 (Open Web Text)

Max Activating Token Index: 396

Text #2

Max Range: 3.3812. Min Range: -3.3812

Max Act: 3.3812. Min Act: -0.1700

Data Index: 4520742 (Open Web Text)

Max Activating Token Index: 648

Text #3

Max Range: 3.3812. Min Range: -3.3812

Max Act: 3.3315. Min Act: -0.1700

Data Index: 6270480 (Open Web Text)

Max Activating Token Index: 796

Text #4

Max Range: 3.3812. Min Range: -3.3812

Max Act: 3.2923. Min Act: -0.1700

Data Index: 4301462 (Open Web Text)

Max Activating Token Index: 499

Text #5

Max Range: 3.3812. Min Range: -3.3812

Max Act: 3.2626. Min Act: -0.1700

Data Index: 1287431 (Open Web Text)

Max Activating Token Index: 793

Text #6

Max Range: 3.3812. Min Range: -3.3812

Max Act: 3.2481. Min Act: -0.1700

Data Index: 8012336 (Open Web Text)

Max Activating Token Index: 808

Text #7

Max Range: 3.3812. Min Range: -3.3812

Max Act: 3.2750. Min Act: -0.1700

Data Index: 3966181 (Open Web Text)

Max Activating Token Index: 564

Text #8

Max Range: 3.3812. Min Range: -3.3812

Max Act: 3.2494. Min Act: -0.1700

Data Index: 4625272 (Open Web Text)

Max Activating Token Index: 496

Text #9

Max Range: 3.3812. Min Range: -3.3812

Max Act: 3.2424. Min Act: -0.1700

Data Index: 2115266 (Open Web Text)

Max Activating Token Index: 141

Text #10

Max Range: 3.3812. Min Range: -3.3812

Max Act: 3.2369. Min Act: -0.1700

Data Index: 1702910 (Open Web Text)

Max Activating Token Index: 101

Text #11

Max Range: 3.3812. Min Range: -3.3812

Max Act: 3.2317. Min Act: -0.1700

Data Index: 6375483 (Open Web Text)

Max Activating Token Index: 979

Text #12

Max Range: 3.3812. Min Range: -3.3812

Max Act: 3.2101. Min Act: -0.1700

Data Index: 3622300 (Open Web Text)

Max Activating Token Index: 136

Text #13

Max Range: 3.3812. Min Range: -3.3812

Max Act: 3.1975. Min Act: -0.1700

Data Index: 1549691 (Open Web Text)

Max Activating Token Index: 657

Text #14

Max Range: 3.3812. Min Range: -3.3812

Max Act: 3.2222. Min Act: -0.1700

Data Index: 8005534 (Open Web Text)

Max Activating Token Index: 99

Text #15

Max Range: 3.3812. Min Range: -3.3812

Max Act: 3.2158. Min Act: -0.1700

Data Index: 6908547 (Open Web Text)

Max Activating Token Index: 48

Text #16

Max Range: 3.3812. Min Range: -3.3812

Max Act: 3.1849. Min Act: -0.1700

Data Index: 5511604 (Open Web Text)

Max Activating Token Index: 26

Text #17

Max Range: 3.3812. Min Range: -3.3812

Max Act: 3.1742. Min Act: -0.1700

Data Index: 2130511 (Open Web Text)

Max Activating Token Index: 779

Text #18

Max Range: 3.3812. Min Range: -3.3812

Max Act: 3.1993. Min Act: -0.1700

Data Index: 2420575 (Open Web Text)

Max Activating Token Index: 932

Text #19

Max Range: 3.3812. Min Range: -3.3812

Max Act: 3.2068. Min Act: -0.1700

Data Index: 7735827 (Open Web Text)

Max Activating Token Index: 292