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

Dataset: Open Web Text

Neuron 1624 in Layer 4

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: 3.4825. Min Range: -3.4825

Max Act: 3.4825. Min Act: -0.1700

Data Index: 5081733 (Open Web Text)

Max Activating Token Index: 454

Text #1

Max Range: 3.4825. Min Range: -3.4825

Max Act: 3.3917. Min Act: -0.1700

Data Index: 5929323 (Open Web Text)

Max Activating Token Index: 583

Text #2

Max Range: 3.4825. Min Range: -3.4825

Max Act: 3.4116. Min Act: -0.1700

Data Index: 6425480 (Open Web Text)

Max Activating Token Index: 418

Text #3

Max Range: 3.4825. Min Range: -3.4825

Max Act: 3.4262. Min Act: -0.1700

Data Index: 3026031 (Open Web Text)

Max Activating Token Index: 509

Text #4

Max Range: 3.4825. Min Range: -3.4825

Max Act: 3.4117. Min Act: -0.1700

Data Index: 4881471 (Open Web Text)

Max Activating Token Index: 401

Text #5

Max Range: 3.4825. Min Range: -3.4825

Max Act: 3.3766. Min Act: -0.1700

Data Index: 1512028 (Open Web Text)

Max Activating Token Index: 226

Text #6

Max Range: 3.4825. Min Range: -3.4825

Max Act: 3.3668. Min Act: -0.1700

Data Index: 6813932 (Open Web Text)

Max Activating Token Index: 522

Text #7

Max Range: 3.4825. Min Range: -3.4825

Max Act: 3.3605. Min Act: -0.1700

Data Index: 7729917 (Open Web Text)

Max Activating Token Index: 416

Text #8

Max Range: 3.4825. Min Range: -3.4825

Max Act: 3.3647. Min Act: -0.1700

Data Index: 7052980 (Open Web Text)

Max Activating Token Index: 134

Text #9

Max Range: 3.4825. Min Range: -3.4825

Max Act: 3.3643. Min Act: -0.1700

Data Index: 8287775 (Open Web Text)

Max Activating Token Index: 190

Text #10

Max Range: 3.4825. Min Range: -3.4825

Max Act: 3.3351. Min Act: -0.1700

Data Index: 2746716 (Open Web Text)

Max Activating Token Index: 413

Text #11

Max Range: 3.4825. Min Range: -3.4825

Max Act: 3.3469. Min Act: -0.1700

Data Index: 5661552 (Open Web Text)

Max Activating Token Index: 600

Text #12

Max Range: 3.4825. Min Range: -3.4825

Max Act: 3.3121. Min Act: -0.1700

Data Index: 3527231 (Open Web Text)

Max Activating Token Index: 500

Text #13

Max Range: 3.4825. Min Range: -3.4825

Max Act: 3.3219. Min Act: -0.1700

Data Index: 6777704 (Open Web Text)

Max Activating Token Index: 85

Text #14

Max Range: 3.4825. Min Range: -3.4825

Max Act: 3.3373. Min Act: -0.1700

Data Index: 5290953 (Open Web Text)

Max Activating Token Index: 275

Text #15

Max Range: 3.4825. Min Range: -3.4825

Max Act: 3.3191. Min Act: -0.1700

Data Index: 3057751 (Open Web Text)

Max Activating Token Index: 336

Text #16

Max Range: 3.4825. Min Range: -3.4825

Max Act: 3.3297. Min Act: -0.1700

Data Index: 6715627 (Open Web Text)

Max Activating Token Index: 844

Text #17

Max Range: 3.4825. Min Range: -3.4825

Max Act: 3.3072. Min Act: -0.1700

Data Index: 2435088 (Open Web Text)

Max Activating Token Index: 448

Text #18

Max Range: 3.4825. Min Range: -3.4825

Max Act: 3.3123. Min Act: -0.1700

Data Index: 1034221 (Open Web Text)

Max Activating Token Index: 649

Text #19

Max Range: 3.4825. Min Range: -3.4825

Max Act: 3.3174. Min Act: -0.1700

Data Index: 7914885 (Open Web Text)

Max Activating Token Index: 641