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

Dataset: Open Web Text

Neuron 4068 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.8080. Min Act: -0.1700

Data Index: 4909744 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.7767. Min Act: -0.1700

Data Index: 1013950 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.7767. Min Act: -0.1700

Data Index: 6109936 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.7767. Min Act: -0.1700

Data Index: 7688962 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.7141. Min Act: -0.1700

Data Index: 7592525 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.7141. Min Act: -0.1700

Data Index: 4677688 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.7141. Min Act: -0.1700

Data Index: 8297250 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6828. Min Act: -0.1700

Data Index: 6379584 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6828. Min Act: -0.1700

Data Index: 4197419 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6828. Min Act: -0.1700

Data Index: 256058 (Open Web Text)

Max Activating Token Index: 15

Text #10

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6828. Min Act: -0.1700

Data Index: 1656182 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6828. Min Act: -0.1700

Data Index: 3319423 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6828. Min Act: -0.1700

Data Index: 120593 (Open Web Text)

Max Activating Token Index: 26

Text #13

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6828. Min Act: -0.1700

Data Index: 7773759 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6828. Min Act: -0.1700

Data Index: 7018551 (Open Web Text)

Max Activating Token Index: 34

Text #15

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6828. Min Act: -0.1700

Data Index: 780131 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6828. Min Act: -0.1700

Data Index: 780135 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6828. Min Act: -0.1700

Data Index: 6797831 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6515. Min Act: -0.1700

Data Index: 1066196 (Open Web Text)

Max Activating Token Index: 13

Text #19

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6515. Min Act: -0.1700

Data Index: 4410316 (Open Web Text)

Max Activating Token Index: 2