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

Dataset: Open Web Text

Neuron 2644 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: 3.6227. Min Range: -3.6227

Max Act: 3.5921. Min Act: -0.1700

Data Index: 7751224 (Open Web Text)

Max Activating Token Index: 34

Text #1

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.6227. Min Act: -0.1700

Data Index: 6906752 (Open Web Text)

Max Activating Token Index: 334

Text #2

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.5798. Min Act: -0.1700

Data Index: 2797133 (Open Web Text)

Max Activating Token Index: 630

Text #3

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.5581. Min Act: -0.1700

Data Index: 8190262 (Open Web Text)

Max Activating Token Index: 886

Text #4

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.5747. Min Act: -0.1700

Data Index: 5400741 (Open Web Text)

Max Activating Token Index: 941

Text #5

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.5793. Min Act: -0.1700

Data Index: 6562769 (Open Web Text)

Max Activating Token Index: 344

Text #6

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.5656. Min Act: -0.1700

Data Index: 8669469 (Open Web Text)

Max Activating Token Index: 865

Text #7

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.5234. Min Act: -0.1700

Data Index: 2054189 (Open Web Text)

Max Activating Token Index: 566

Text #8

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.5242. Min Act: -0.1700

Data Index: 313744 (Open Web Text)

Max Activating Token Index: 905

Text #9

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.5160. Min Act: -0.1700

Data Index: 6094703 (Open Web Text)

Max Activating Token Index: 570

Text #10

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.4988. Min Act: -0.1700

Data Index: 8257358 (Open Web Text)

Max Activating Token Index: 615

Text #11

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.5017. Min Act: -0.1700

Data Index: 600721 (Open Web Text)

Max Activating Token Index: 67

Text #12

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.5122. Min Act: -0.1700

Data Index: 5856475 (Open Web Text)

Max Activating Token Index: 1006

Text #13

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.4762. Min Act: -0.1700

Data Index: 505316 (Open Web Text)

Max Activating Token Index: 982

Text #14

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.4928. Min Act: -0.1700

Data Index: 5808787 (Open Web Text)

Max Activating Token Index: 25

Text #15

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.4887. Min Act: -0.1700

Data Index: 4633308 (Open Web Text)

Max Activating Token Index: 642

Text #16

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.4798. Min Act: -0.1700

Data Index: 958545 (Open Web Text)

Max Activating Token Index: 725

Text #17

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.5057. Min Act: -0.1700

Data Index: 4610555 (Open Web Text)

Max Activating Token Index: 508

Text #18

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.4876. Min Act: -0.1700

Data Index: 376946 (Open Web Text)

Max Activating Token Index: 731

Text #19

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.4564. Min Act: -0.1700

Data Index: 6406231 (Open Web Text)

Max Activating Token Index: 127