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

Dataset: Open Web Text

Neuron 2469 in Layer 5

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: 5.3454. Min Range: -5.3454

Max Act: 5.3454. Min Act: -0.1700

Data Index: 6127089 (Open Web Text)

Max Activating Token Index: 565

Text #1

Max Range: 5.3454. Min Range: -5.3454

Max Act: 5.3188. Min Act: -0.1700

Data Index: 7754451 (Open Web Text)

Max Activating Token Index: 770

Text #2

Max Range: 5.3454. Min Range: -5.3454

Max Act: 5.2968. Min Act: -0.1700

Data Index: 69790 (Open Web Text)

Max Activating Token Index: 858

Text #3

Max Range: 5.3454. Min Range: -5.3454

Max Act: 5.3437. Min Act: -0.1700

Data Index: 2511594 (Open Web Text)

Max Activating Token Index: 945

Text #4

Max Range: 5.3454. Min Range: -5.3454

Max Act: 5.2758. Min Act: -0.1700

Data Index: 3578699 (Open Web Text)

Max Activating Token Index: 737

Text #5

Max Range: 5.3454. Min Range: -5.3454

Max Act: 5.2099. Min Act: -0.1700

Data Index: 3853995 (Open Web Text)

Max Activating Token Index: 418

Text #6

Max Range: 5.3454. Min Range: -5.3454

Max Act: 5.2704. Min Act: -0.1700

Data Index: 360301 (Open Web Text)

Max Activating Token Index: 869

Text #7

Max Range: 5.3454. Min Range: -5.3454

Max Act: 5.1849. Min Act: -0.1700

Data Index: 5294601 (Open Web Text)

Max Activating Token Index: 512

Text #8

Max Range: 5.3454. Min Range: -5.3454

Max Act: 5.2050. Min Act: -0.1700

Data Index: 3005470 (Open Web Text)

Max Activating Token Index: 667

Text #9

Max Range: 5.3454. Min Range: -5.3454

Max Act: 5.2211. Min Act: -0.1700

Data Index: 3586457 (Open Web Text)

Max Activating Token Index: 994

Text #10

Max Range: 5.3454. Min Range: -5.3454

Max Act: 5.1967. Min Act: -0.1700

Data Index: 4420358 (Open Web Text)

Max Activating Token Index: 860

Text #11

Max Range: 5.3454. Min Range: -5.3454

Max Act: 5.2280. Min Act: -0.1700

Data Index: 525922 (Open Web Text)

Max Activating Token Index: 769

Text #12

Max Range: 5.3454. Min Range: -5.3454

Max Act: 5.2506. Min Act: -0.1700

Data Index: 2377201 (Open Web Text)

Max Activating Token Index: 788

Text #13

Max Range: 5.3454. Min Range: -5.3454

Max Act: 5.2311. Min Act: -0.1700

Data Index: 5503997 (Open Web Text)

Max Activating Token Index: 1019

Text #14

Max Range: 5.3454. Min Range: -5.3454

Max Act: 5.1743. Min Act: -0.1700

Data Index: 8583069 (Open Web Text)

Max Activating Token Index: 798

Text #15

Max Range: 5.3454. Min Range: -5.3454

Max Act: 5.1361. Min Act: -0.1700

Data Index: 1299661 (Open Web Text)

Max Activating Token Index: 532

Text #16

Max Range: 5.3454. Min Range: -5.3454

Max Act: 5.1689. Min Act: -0.1700

Data Index: 3829657 (Open Web Text)

Max Activating Token Index: 822

Text #17

Max Range: 5.3454. Min Range: -5.3454

Max Act: 5.1419. Min Act: -0.1700

Data Index: 2741027 (Open Web Text)

Max Activating Token Index: 231

Text #18

Max Range: 5.3454. Min Range: -5.3454

Max Act: 5.1438. Min Act: -0.1700

Data Index: 3682899 (Open Web Text)

Max Activating Token Index: 429

Text #19

Max Range: 5.3454. Min Range: -5.3454

Max Act: 5.1420. Min Act: -0.1700

Data Index: 5117270 (Open Web Text)

Max Activating Token Index: 725