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

Dataset: Open Web Text

Neuron 651 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: 4.7496. Min Range: -4.7496

Max Act: 4.7496. Min Act: -0.1700

Data Index: 4359580 (Open Web Text)

Max Activating Token Index: 624

Text #1

Max Range: 4.7496. Min Range: -4.7496

Max Act: 4.6350. Min Act: -0.1700

Data Index: 4082899 (Open Web Text)

Max Activating Token Index: 593

Text #2

Max Range: 4.7496. Min Range: -4.7496

Max Act: 4.6397. Min Act: -0.1700

Data Index: 512123 (Open Web Text)

Max Activating Token Index: 868

Text #3

Max Range: 4.7496. Min Range: -4.7496

Max Act: 4.6044. Min Act: -0.1700

Data Index: 3923858 (Open Web Text)

Max Activating Token Index: 75

Text #4

Max Range: 4.7496. Min Range: -4.7496

Max Act: 4.6101. Min Act: -0.1700

Data Index: 5795588 (Open Web Text)

Max Activating Token Index: 46

Text #5

Max Range: 4.7496. Min Range: -4.7496

Max Act: 4.5907. Min Act: -0.1700

Data Index: 3485148 (Open Web Text)

Max Activating Token Index: 185

Text #6

Max Range: 4.7496. Min Range: -4.7496

Max Act: 4.5377. Min Act: -0.1700

Data Index: 7774724 (Open Web Text)

Max Activating Token Index: 787

Text #7

Max Range: 4.7496. Min Range: -4.7496

Max Act: 4.5241. Min Act: -0.1700

Data Index: 8625049 (Open Web Text)

Max Activating Token Index: 419

Text #8

Max Range: 4.7496. Min Range: -4.7496

Max Act: 4.5101. Min Act: -0.1700

Data Index: 7025642 (Open Web Text)

Max Activating Token Index: 531

Text #9

Max Range: 4.7496. Min Range: -4.7496

Max Act: 4.5478. Min Act: -0.1700

Data Index: 4528296 (Open Web Text)

Max Activating Token Index: 260

Text #10

Max Range: 4.7496. Min Range: -4.7496

Max Act: 4.5127. Min Act: -0.1700

Data Index: 4937849 (Open Web Text)

Max Activating Token Index: 321

Text #11

Max Range: 4.7496. Min Range: -4.7496

Max Act: 4.5212. Min Act: -0.1700

Data Index: 3159828 (Open Web Text)

Max Activating Token Index: 916

Text #12

Max Range: 4.7496. Min Range: -4.7496

Max Act: 4.5188. Min Act: -0.1700

Data Index: 5968967 (Open Web Text)

Max Activating Token Index: 130

Text #13

Max Range: 4.7496. Min Range: -4.7496

Max Act: 4.5145. Min Act: -0.1700

Data Index: 902014 (Open Web Text)

Max Activating Token Index: 485

Text #14

Max Range: 4.7496. Min Range: -4.7496

Max Act: 4.4998. Min Act: -0.1700

Data Index: 6836361 (Open Web Text)

Max Activating Token Index: 128

Text #15

Max Range: 4.7496. Min Range: -4.7496

Max Act: 4.5087. Min Act: -0.1700

Data Index: 3472888 (Open Web Text)

Max Activating Token Index: 936

Text #16

Max Range: 4.7496. Min Range: -4.7496

Max Act: 4.4903. Min Act: -0.1700

Data Index: 3957699 (Open Web Text)

Max Activating Token Index: 962

Text #17

Max Range: 4.7496. Min Range: -4.7496

Max Act: 4.4789. Min Act: -0.1700

Data Index: 1968584 (Open Web Text)

Max Activating Token Index: 160

Text #18

Max Range: 4.7496. Min Range: -4.7496

Max Act: 4.4844. Min Act: -0.1700

Data Index: 5440226 (Open Web Text)

Max Activating Token Index: 509

Text #19

Max Range: 4.7496. Min Range: -4.7496

Max Act: 4.4839. Min Act: -0.1700

Data Index: 6436775 (Open Web Text)

Max Activating Token Index: 579