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

Dataset: Open Web Text

Neuron 2785 in Layer 6

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: 4.6373. Min Range: -4.6373

Max Act: 4.6373. Min Act: -0.1700

Data Index: 4191877 (Open Web Text)

Max Activating Token Index: 235

Text #1

Max Range: 4.6373. Min Range: -4.6373

Max Act: 4.6086. Min Act: -0.1700

Data Index: 4012511 (Open Web Text)

Max Activating Token Index: 1007

Text #2

Max Range: 4.6373. Min Range: -4.6373

Max Act: 4.5839. Min Act: -0.1700

Data Index: 5988456 (Open Web Text)

Max Activating Token Index: 890

Text #3

Max Range: 4.6373. Min Range: -4.6373

Max Act: 4.5266. Min Act: -0.1700

Data Index: 391005 (Open Web Text)

Max Activating Token Index: 550

Text #4

Max Range: 4.6373. Min Range: -4.6373

Max Act: 4.4920. Min Act: -0.1700

Data Index: 6506525 (Open Web Text)

Max Activating Token Index: 656

Text #5

Max Range: 4.6373. Min Range: -4.6373

Max Act: 4.4615. Min Act: -0.1700

Data Index: 2553752 (Open Web Text)

Max Activating Token Index: 537

Text #6

Max Range: 4.6373. Min Range: -4.6373

Max Act: 4.4383. Min Act: -0.1700

Data Index: 4444361 (Open Web Text)

Max Activating Token Index: 882

Text #7

Max Range: 4.6373. Min Range: -4.6373

Max Act: 4.4374. Min Act: -0.1700

Data Index: 8382320 (Open Web Text)

Max Activating Token Index: 180

Text #8

Max Range: 4.6373. Min Range: -4.6373

Max Act: 4.4326. Min Act: -0.1700

Data Index: 6864848 (Open Web Text)

Max Activating Token Index: 789

Text #9

Max Range: 4.6373. Min Range: -4.6373

Max Act: 4.4150. Min Act: -0.1700

Data Index: 8165241 (Open Web Text)

Max Activating Token Index: 904

Text #10

Max Range: 4.6373. Min Range: -4.6373

Max Act: 4.4225. Min Act: -0.1700

Data Index: 6264322 (Open Web Text)

Max Activating Token Index: 641

Text #11

Max Range: 4.6373. Min Range: -4.6373

Max Act: 4.4139. Min Act: -0.1700

Data Index: 2272852 (Open Web Text)

Max Activating Token Index: 674

Text #12

Max Range: 4.6373. Min Range: -4.6373

Max Act: 4.3878. Min Act: -0.1700

Data Index: 6038678 (Open Web Text)

Max Activating Token Index: 358

Text #13

Max Range: 4.6373. Min Range: -4.6373

Max Act: 4.3901. Min Act: -0.1700

Data Index: 1419624 (Open Web Text)

Max Activating Token Index: 910

Text #14

Max Range: 4.6373. Min Range: -4.6373

Max Act: 4.4032. Min Act: -0.1700

Data Index: 7110357 (Open Web Text)

Max Activating Token Index: 65

Text #15

Max Range: 4.6373. Min Range: -4.6373

Max Act: 4.4072. Min Act: -0.1700

Data Index: 5030543 (Open Web Text)

Max Activating Token Index: 76

Text #16

Max Range: 4.6373. Min Range: -4.6373

Max Act: 4.4181. Min Act: -0.1700

Data Index: 4735194 (Open Web Text)

Max Activating Token Index: 1016

Text #17

Max Range: 4.6373. Min Range: -4.6373

Max Act: 4.3888. Min Act: -0.1700

Data Index: 3359304 (Open Web Text)

Max Activating Token Index: 502

Text #18

Max Range: 4.6373. Min Range: -4.6373

Max Act: 4.3858. Min Act: -0.1700

Data Index: 1025079 (Open Web Text)

Max Activating Token Index: 236

Text #19

Max Range: 4.6373. Min Range: -4.6373

Max Act: 4.3631. Min Act: -0.1700

Data Index: 1684729 (Open Web Text)

Max Activating Token Index: 689