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

Dataset: Open Web Text

Neuron 1302 in Layer 0

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: 5.2516. Min Range: -5.2516

Max Act: 5.2516. Min Act: -0.1700

Data Index: 6874108 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 5.2516. Min Range: -5.2516

Max Act: 5.0181. Min Act: -0.1700

Data Index: 7669695 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.7802. Min Act: -0.1700

Data Index: 7075731 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.7600. Min Act: -0.1700

Data Index: 3468828 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.7868. Min Act: -0.1700

Data Index: 1131931 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.7195. Min Act: -0.1700

Data Index: 240470 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.6531. Min Act: -0.1700

Data Index: 4617494 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.6250. Min Act: -0.1700

Data Index: 8178823 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.6290. Min Act: -0.1700

Data Index: 4590534 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.6266. Min Act: -0.1700

Data Index: 4455257 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.6276. Min Act: -0.1700

Data Index: 2546834 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.6185. Min Act: -0.1700

Data Index: 1436348 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.6386. Min Act: -0.1700

Data Index: 4783541 (Open Web Text)

Max Activating Token Index: 13

Text #13

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.6332. Min Act: -0.1700

Data Index: 1728212 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.6385. Min Act: -0.1700

Data Index: 3135785 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.6348. Min Act: -0.1700

Data Index: 7465439 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.6297. Min Act: -0.1700

Data Index: 1659650 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.5943. Min Act: -0.1700

Data Index: 3285786 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.6008. Min Act: -0.1700

Data Index: 2813962 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 5.2516. Min Range: -5.2516

Max Act: 4.5771. Min Act: -0.1700

Data Index: 4455500 (Open Web Text)

Max Activating Token Index: 13