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

Dataset: Open Web Text

Neuron 517 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: 4.8695. Min Range: -4.8695

Max Act: 4.8695. Min Act: -0.1700

Data Index: 7670283 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.6863. Min Act: -0.1700

Data Index: 792733 (Open Web Text)

Max Activating Token Index: 750

Text #2

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.6757. Min Act: -0.1700

Data Index: 1409046 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.6450. Min Act: -0.1700

Data Index: 5783110 (Open Web Text)

Max Activating Token Index: 760

Text #4

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.6355. Min Act: -0.1700

Data Index: 1712267 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.6180. Min Act: -0.1700

Data Index: 230081 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.6163. Min Act: -0.1700

Data Index: 2981759 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.5985. Min Act: -0.1700

Data Index: 4472861 (Open Web Text)

Max Activating Token Index: 190

Text #8

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.5829. Min Act: -0.1700

Data Index: 840878 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.5895. Min Act: -0.1700

Data Index: 818209 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.5827. Min Act: -0.1700

Data Index: 8423390 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.5773. Min Act: -0.1700

Data Index: 6909014 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.5774. Min Act: -0.1700

Data Index: 3313817 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.5627. Min Act: -0.1700

Data Index: 8063228 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.5631. Min Act: -0.1700

Data Index: 1758016 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.5696. Min Act: -0.1700

Data Index: 4097201 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.5727. Min Act: -0.1700

Data Index: 3119946 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.5258. Min Act: -0.1700

Data Index: 4177402 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.5268. Min Act: -0.1700

Data Index: 2807010 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 4.8695. Min Range: -4.8695

Max Act: 4.5237. Min Act: -0.1700

Data Index: 1174364 (Open Web Text)

Max Activating Token Index: 812