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

Dataset: Open Web Text

Neuron 2790 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: 4.9987. Min Range: -4.9987

Max Act: 4.9987. Min Act: -0.1700

Data Index: 740295 (Open Web Text)

Max Activating Token Index: 804

Text #1

Max Range: 4.9987. Min Range: -4.9987

Max Act: 4.9531. Min Act: -0.1700

Data Index: 315778 (Open Web Text)

Max Activating Token Index: 779

Text #2

Max Range: 4.9987. Min Range: -4.9987

Max Act: 4.9478. Min Act: -0.1700

Data Index: 5670340 (Open Web Text)

Max Activating Token Index: 480

Text #3

Max Range: 4.9987. Min Range: -4.9987

Max Act: 4.9158. Min Act: -0.1700

Data Index: 1800146 (Open Web Text)

Max Activating Token Index: 903

Text #4

Max Range: 4.9987. Min Range: -4.9987

Max Act: 4.9185. Min Act: -0.1700

Data Index: 5430872 (Open Web Text)

Max Activating Token Index: 948

Text #5

Max Range: 4.9987. Min Range: -4.9987

Max Act: 4.8462. Min Act: -0.1700

Data Index: 7333992 (Open Web Text)

Max Activating Token Index: 590

Text #6

Max Range: 4.9987. Min Range: -4.9987

Max Act: 4.8783. Min Act: -0.1700

Data Index: 2441644 (Open Web Text)

Max Activating Token Index: 644

Text #7

Max Range: 4.9987. Min Range: -4.9987

Max Act: 4.8427. Min Act: -0.1700

Data Index: 560106 (Open Web Text)

Max Activating Token Index: 800

Text #8

Max Range: 4.9987. Min Range: -4.9987

Max Act: 4.8721. Min Act: -0.1700

Data Index: 3504847 (Open Web Text)

Max Activating Token Index: 831

Text #9

Max Range: 4.9987. Min Range: -4.9987

Max Act: 4.8608. Min Act: -0.1700

Data Index: 254881 (Open Web Text)

Max Activating Token Index: 688

Text #10

Max Range: 4.9987. Min Range: -4.9987

Max Act: 4.8439. Min Act: -0.1700

Data Index: 4472210 (Open Web Text)

Max Activating Token Index: 781

Text #11

Max Range: 4.9987. Min Range: -4.9987

Max Act: 4.8071. Min Act: -0.1700

Data Index: 292670 (Open Web Text)

Max Activating Token Index: 806

Text #12

Max Range: 4.9987. Min Range: -4.9987

Max Act: 4.7868. Min Act: -0.1700

Data Index: 6306218 (Open Web Text)

Max Activating Token Index: 818

Text #13

Max Range: 4.9987. Min Range: -4.9987

Max Act: 4.7801. Min Act: -0.1700

Data Index: 3748032 (Open Web Text)

Max Activating Token Index: 688

Text #14

Max Range: 4.9987. Min Range: -4.9987

Max Act: 4.8374. Min Act: -0.1700

Data Index: 4000815 (Open Web Text)

Max Activating Token Index: 400

Text #15

Max Range: 4.9987. Min Range: -4.9987

Max Act: 4.7635. Min Act: -0.1700

Data Index: 3679171 (Open Web Text)

Max Activating Token Index: 676

Text #16

Max Range: 4.9987. Min Range: -4.9987

Max Act: 4.7145. Min Act: -0.1700

Data Index: 2568848 (Open Web Text)

Max Activating Token Index: 667

Text #17

Max Range: 4.9987. Min Range: -4.9987

Max Act: 4.7233. Min Act: -0.1700

Data Index: 7298354 (Open Web Text)

Max Activating Token Index: 939

Text #18

Max Range: 4.9987. Min Range: -4.9987

Max Act: 4.7287. Min Act: -0.1700

Data Index: 24437 (Open Web Text)

Max Activating Token Index: 851

Text #19

Max Range: 4.9987. Min Range: -4.9987

Max Act: 4.7698. Min Act: -0.1700

Data Index: 4055553 (Open Web Text)

Max Activating Token Index: 738