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

Dataset: Open Web Text

Neuron 1836 in Layer 2

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: 4.4025. Min Range: -4.4025

Max Act: 4.4025. Min Act: -0.1700

Data Index: 4984879 (Open Web Text)

Max Activating Token Index: 22

Text #1

Max Range: 4.4025. Min Range: -4.4025

Max Act: 4.3218. Min Act: -0.1699

Data Index: 6413524 (Open Web Text)

Max Activating Token Index: 863

Text #2

Max Range: 4.4025. Min Range: -4.4025

Max Act: 4.2517. Min Act: -0.1700

Data Index: 4921101 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.4025. Min Range: -4.4025

Max Act: 4.2261. Min Act: -0.1699

Data Index: 8017672 (Open Web Text)

Max Activating Token Index: 387

Text #4

Max Range: 4.4025. Min Range: -4.4025

Max Act: 4.2411. Min Act: -0.1700

Data Index: 1943544 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.4025. Min Range: -4.4025

Max Act: 4.2221. Min Act: -0.1700

Data Index: 7497515 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.4025. Min Range: -4.4025

Max Act: 4.2025. Min Act: -0.1700

Data Index: 4748147 (Open Web Text)

Max Activating Token Index: 850

Text #7

Max Range: 4.4025. Min Range: -4.4025

Max Act: 4.2039. Min Act: -0.1700

Data Index: 8739898 (Open Web Text)

Max Activating Token Index: 179

Text #8

Max Range: 4.4025. Min Range: -4.4025

Max Act: 4.1979. Min Act: -0.1700

Data Index: 8630554 (Open Web Text)

Max Activating Token Index: 490

Text #9

Max Range: 4.4025. Min Range: -4.4025

Max Act: 4.1903. Min Act: -0.1700

Data Index: 4233048 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.4025. Min Range: -4.4025

Max Act: 4.2178. Min Act: -0.1700

Data Index: 4128012 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.4025. Min Range: -4.4025

Max Act: 4.1824. Min Act: -0.1699

Data Index: 5011985 (Open Web Text)

Max Activating Token Index: 846

Text #12

Max Range: 4.4025. Min Range: -4.4025

Max Act: 4.1988. Min Act: -0.1700

Data Index: 2535043 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 4.4025. Min Range: -4.4025

Max Act: 4.2188. Min Act: -0.1700

Data Index: 481282 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.4025. Min Range: -4.4025

Max Act: 4.2231. Min Act: -0.1700

Data Index: 3538046 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.4025. Min Range: -4.4025

Max Act: 4.2077. Min Act: -0.1700

Data Index: 3306226 (Open Web Text)

Max Activating Token Index: 150

Text #16

Max Range: 4.4025. Min Range: -4.4025

Max Act: 4.1903. Min Act: -0.1700

Data Index: 4955031 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.4025. Min Range: -4.4025

Max Act: 4.1956. Min Act: -0.1700

Data Index: 2612464 (Open Web Text)

Max Activating Token Index: 866

Text #18

Max Range: 4.4025. Min Range: -4.4025

Max Act: 4.1851. Min Act: -0.1700

Data Index: 2993633 (Open Web Text)

Max Activating Token Index: 1022

Text #19

Max Range: 4.4025. Min Range: -4.4025

Max Act: 4.1690. Min Act: -0.1700

Data Index: 75597 (Open Web Text)

Max Activating Token Index: 5