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

Dataset: Open Web Text

Neuron 1820 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: 4.5874. Min Range: -4.5874

Max Act: 4.5874. Min Act: -0.1700

Data Index: 8801697 (Open Web Text)

Max Activating Token Index: 755

Text #1

Max Range: 4.5874. Min Range: -4.5874

Max Act: 4.5435. Min Act: -0.1700

Data Index: 1189042 (Open Web Text)

Max Activating Token Index: 436

Text #2

Max Range: 4.5874. Min Range: -4.5874

Max Act: 4.4516. Min Act: -0.1700

Data Index: 7497918 (Open Web Text)

Max Activating Token Index: 221

Text #3

Max Range: 4.5874. Min Range: -4.5874

Max Act: 4.4111. Min Act: -0.1700

Data Index: 891399 (Open Web Text)

Max Activating Token Index: 498

Text #4

Max Range: 4.5874. Min Range: -4.5874

Max Act: 4.3990. Min Act: -0.1700

Data Index: 4819934 (Open Web Text)

Max Activating Token Index: 171

Text #5

Max Range: 4.5874. Min Range: -4.5874

Max Act: 4.3905. Min Act: -0.1700

Data Index: 5923385 (Open Web Text)

Max Activating Token Index: 653

Text #6

Max Range: 4.5874. Min Range: -4.5874

Max Act: 4.3829. Min Act: -0.1700

Data Index: 5392573 (Open Web Text)

Max Activating Token Index: 870

Text #7

Max Range: 4.5874. Min Range: -4.5874

Max Act: 4.3574. Min Act: -0.1700

Data Index: 2750353 (Open Web Text)

Max Activating Token Index: 461

Text #8

Max Range: 4.5874. Min Range: -4.5874

Max Act: 4.3912. Min Act: -0.1700

Data Index: 2357561 (Open Web Text)

Max Activating Token Index: 706

Text #9

Max Range: 4.5874. Min Range: -4.5874

Max Act: 4.3414. Min Act: -0.1700

Data Index: 5040420 (Open Web Text)

Max Activating Token Index: 506

Text #10

Max Range: 4.5874. Min Range: -4.5874

Max Act: 4.3069. Min Act: -0.1700

Data Index: 4804243 (Open Web Text)

Max Activating Token Index: 25

Text #11

Max Range: 4.5874. Min Range: -4.5874

Max Act: 4.3120. Min Act: -0.1700

Data Index: 1761698 (Open Web Text)

Max Activating Token Index: 1005

Text #12

Max Range: 4.5874. Min Range: -4.5874

Max Act: 4.3302. Min Act: -0.1700

Data Index: 7879524 (Open Web Text)

Max Activating Token Index: 545

Text #13

Max Range: 4.5874. Min Range: -4.5874

Max Act: 4.3290. Min Act: -0.1700

Data Index: 1125296 (Open Web Text)

Max Activating Token Index: 443

Text #14

Max Range: 4.5874. Min Range: -4.5874

Max Act: 4.3293. Min Act: -0.1700

Data Index: 7324867 (Open Web Text)

Max Activating Token Index: 721

Text #15

Max Range: 4.5874. Min Range: -4.5874

Max Act: 4.3343. Min Act: -0.1700

Data Index: 7994321 (Open Web Text)

Max Activating Token Index: 432

Text #16

Max Range: 4.5874. Min Range: -4.5874

Max Act: 4.3173. Min Act: -0.1700

Data Index: 3180493 (Open Web Text)

Max Activating Token Index: 414

Text #17

Max Range: 4.5874. Min Range: -4.5874

Max Act: 4.2601. Min Act: -0.1700

Data Index: 5837794 (Open Web Text)

Max Activating Token Index: 654

Text #18

Max Range: 4.5874. Min Range: -4.5874

Max Act: 4.2653. Min Act: -0.1700

Data Index: 4827620 (Open Web Text)

Max Activating Token Index: 535

Text #19

Max Range: 4.5874. Min Range: -4.5874

Max Act: 4.2576. Min Act: -0.1700

Data Index: 1323073 (Open Web Text)

Max Activating Token Index: 362