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

Dataset: Open Web Text

Neuron 2484 in Layer 1

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: 4.7987. Min Range: -4.7987

Max Act: 4.7966. Min Act: -0.1700

Data Index: 3939929 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 4.7987. Min Range: -4.7987

Max Act: 4.7987. Min Act: -0.1700

Data Index: 2842060 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 4.7987. Min Range: -4.7987

Max Act: 4.7305. Min Act: -0.1700

Data Index: 741918 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.7987. Min Range: -4.7987

Max Act: 4.7033. Min Act: -0.1700

Data Index: 353646 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.7987. Min Range: -4.7987

Max Act: 4.7033. Min Act: -0.1700

Data Index: 3428968 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.7987. Min Range: -4.7987

Max Act: 4.6951. Min Act: -0.1700

Data Index: 3668891 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.7987. Min Range: -4.7987

Max Act: 4.6921. Min Act: -0.1700

Data Index: 8651715 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 4.7987. Min Range: -4.7987

Max Act: 4.7008. Min Act: -0.1700

Data Index: 651624 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.7987. Min Range: -4.7987

Max Act: 4.6440. Min Act: -0.1700

Data Index: 1170192 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.7987. Min Range: -4.7987

Max Act: 4.6422. Min Act: -0.1700

Data Index: 869898 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.7987. Min Range: -4.7987

Max Act: 4.6186. Min Act: -0.1700

Data Index: 6595853 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.7987. Min Range: -4.7987

Max Act: 4.5844. Min Act: -0.1700

Data Index: 6874845 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.7987. Min Range: -4.7987

Max Act: 4.6069. Min Act: -0.1700

Data Index: 7123787 (Open Web Text)

Max Activating Token Index: 13

Text #13

Max Range: 4.7987. Min Range: -4.7987

Max Act: 4.5914. Min Act: -0.1700

Data Index: 4510903 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.7987. Min Range: -4.7987

Max Act: 4.5863. Min Act: -0.1700

Data Index: 3708347 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 4.7987. Min Range: -4.7987

Max Act: 4.5950. Min Act: -0.1700

Data Index: 2345202 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.7987. Min Range: -4.7987

Max Act: 4.5960. Min Act: -0.1700

Data Index: 7656279 (Open Web Text)

Max Activating Token Index: 465

Text #17

Max Range: 4.7987. Min Range: -4.7987

Max Act: 4.6143. Min Act: -0.1700

Data Index: 6301864 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.7987. Min Range: -4.7987

Max Act: 4.5575. Min Act: -0.1700

Data Index: 4934256 (Open Web Text)

Max Activating Token Index: 157

Text #19

Max Range: 4.7987. Min Range: -4.7987

Max Act: 4.5622. Min Act: -0.1700

Data Index: 5007358 (Open Web Text)

Max Activating Token Index: 227