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

Dataset: Open Web Text

Neuron 1490 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: 2.8570. Min Range: -2.8570

Max Act: 2.8570. Min Act: -0.1700

Data Index: 4799620 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.8570. Min Range: -2.8570

Max Act: 2.8087. Min Act: -0.1700

Data Index: 3206676 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.8570. Min Range: -2.8570

Max Act: 2.7955. Min Act: -0.1700

Data Index: 2156294 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 2.8570. Min Range: -2.8570

Max Act: 2.8010. Min Act: -0.1700

Data Index: 5705402 (Open Web Text)

Max Activating Token Index: 21

Text #4

Max Range: 2.8570. Min Range: -2.8570

Max Act: 2.7960. Min Act: -0.1700

Data Index: 5058871 (Open Web Text)

Max Activating Token Index: 21

Text #5

Max Range: 2.8570. Min Range: -2.8570

Max Act: 2.7856. Min Act: -0.1700

Data Index: 6430457 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 2.8570. Min Range: -2.8570

Max Act: 2.7843. Min Act: -0.1700

Data Index: 6622532 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.8570. Min Range: -2.8570

Max Act: 2.7904. Min Act: -0.1700

Data Index: 4891401 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.8570. Min Range: -2.8570

Max Act: 2.7722. Min Act: -0.1700

Data Index: 8519901 (Open Web Text)

Max Activating Token Index: 15

Text #9

Max Range: 2.8570. Min Range: -2.8570

Max Act: 2.7582. Min Act: -0.1700

Data Index: 5237029 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 2.8570. Min Range: -2.8570

Max Act: 2.7641. Min Act: -0.1700

Data Index: 8474790 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.8570. Min Range: -2.8570

Max Act: 2.7709. Min Act: -0.1700

Data Index: 3242139 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 2.8570. Min Range: -2.8570

Max Act: 2.7579. Min Act: -0.1700

Data Index: 7637287 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 2.8570. Min Range: -2.8570

Max Act: 2.7662. Min Act: -0.1700

Data Index: 804349 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 2.8570. Min Range: -2.8570

Max Act: 2.7674. Min Act: -0.1700

Data Index: 5581116 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 2.8570. Min Range: -2.8570

Max Act: 2.7569. Min Act: -0.1700

Data Index: 8357633 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 2.8570. Min Range: -2.8570

Max Act: 2.7556. Min Act: -0.1700

Data Index: 3853380 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 2.8570. Min Range: -2.8570

Max Act: 2.7503. Min Act: -0.1700

Data Index: 6511005 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.8570. Min Range: -2.8570

Max Act: 2.7434. Min Act: -0.1700

Data Index: 5469613 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 2.8570. Min Range: -2.8570

Max Act: 2.7442. Min Act: -0.1700

Data Index: 947786 (Open Web Text)

Max Activating Token Index: 11