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

Dataset: Open Web Text

Neuron 1509 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: 4.5057. Min Range: -4.5057

Max Act: 4.5057. Min Act: -0.1700

Data Index: 2050493 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.5057. Min Range: -4.5057

Max Act: 4.4081. Min Act: -0.1700

Data Index: 6406970 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.5057. Min Range: -4.5057

Max Act: 4.3065. Min Act: -0.1700

Data Index: 8329783 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.5057. Min Range: -4.5057

Max Act: 4.2676. Min Act: -0.1700

Data Index: 2732365 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.5057. Min Range: -4.5057

Max Act: 4.2452. Min Act: -0.1700

Data Index: 326971 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 4.5057. Min Range: -4.5057

Max Act: 4.2676. Min Act: -0.1700

Data Index: 4134784 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.5057. Min Range: -4.5057

Max Act: 4.2245. Min Act: -0.1700

Data Index: 761766 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.5057. Min Range: -4.5057

Max Act: 4.2022. Min Act: -0.1700

Data Index: 3124169 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.5057. Min Range: -4.5057

Max Act: 4.2162. Min Act: -0.1700

Data Index: 8289593 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.5057. Min Range: -4.5057

Max Act: 4.1997. Min Act: -0.1700

Data Index: 1810464 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 4.5057. Min Range: -4.5057

Max Act: 4.1721. Min Act: -0.1700

Data Index: 4830193 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.5057. Min Range: -4.5057

Max Act: 4.1836. Min Act: -0.1700

Data Index: 448380 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 4.5057. Min Range: -4.5057

Max Act: 4.1736. Min Act: -0.1700

Data Index: 7144263 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 4.5057. Min Range: -4.5057

Max Act: 4.1938. Min Act: -0.1700

Data Index: 8711393 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.5057. Min Range: -4.5057

Max Act: 4.1745. Min Act: -0.1700

Data Index: 536327 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 4.5057. Min Range: -4.5057

Max Act: 4.1901. Min Act: -0.1700

Data Index: 3764780 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 4.5057. Min Range: -4.5057

Max Act: 4.1695. Min Act: -0.1700

Data Index: 531184 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 4.5057. Min Range: -4.5057

Max Act: 4.1695. Min Act: -0.1700

Data Index: 876388 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 4.5057. Min Range: -4.5057

Max Act: 4.1526. Min Act: -0.1700

Data Index: 7500218 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 4.5057. Min Range: -4.5057

Max Act: 4.1524. Min Act: -0.1700

Data Index: 2904336 (Open Web Text)

Max Activating Token Index: 4