Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 1205 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')

Text #0

Max Range: 2.1016. Min Range: -2.1016

Max Act: 2.1016. Min Act: -0.1700

Data Index: 6395833 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 2.1016. Min Range: -2.1016

Max Act: 2.1016. Min Act: -0.1700

Data Index: 7318643 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.1016. Min Range: -2.1016

Max Act: 2.0344. Min Act: -0.1700

Data Index: 1101889 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 2.1016. Min Range: -2.1016

Max Act: 2.0175. Min Act: -0.1700

Data Index: 6306657 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.1016. Min Range: -2.1016

Max Act: 2.0175. Min Act: -0.1700

Data Index: 4165790 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.1016. Min Range: -2.1016

Max Act: 2.0175. Min Act: -0.1700

Data Index: 1188941 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.1016. Min Range: -2.1016

Max Act: 2.0175. Min Act: -0.1700

Data Index: 1556602 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.1016. Min Range: -2.1016

Max Act: 2.0175. Min Act: -0.1700

Data Index: 6421268 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.1016. Min Range: -2.1016

Max Act: 2.0175. Min Act: -0.1700

Data Index: 7530454 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.1016. Min Range: -2.1016

Max Act: 2.0175. Min Act: -0.1700

Data Index: 1501272 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.1016. Min Range: -2.1016

Max Act: 2.0007. Min Act: -0.1700

Data Index: 1148401 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.9498. Min Act: -0.1700

Data Index: 5781201 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.9498. Min Act: -0.1700

Data Index: 5708975 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.9329. Min Act: -0.1700

Data Index: 3309036 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.9329. Min Act: -0.1700

Data Index: 7630929 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.9158. Min Act: -0.1700

Data Index: 1285968 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.9158. Min Act: -0.1700

Data Index: 5889930 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.9158. Min Act: -0.1700

Data Index: 8082428 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.8988. Min Act: -0.1700

Data Index: 4831041 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.8817. Min Act: -0.1700

Data Index: 5068212 (Open Web Text)

Max Activating Token Index: 5