Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 331 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2003. Min Range: -5.2003

Max Act: 5.2003. Min Act: -0.1700

Data Index: 5224852 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 5.2003. Min Range: -5.2003

Max Act: 5.2003. Min Act: -0.1700

Data Index: 6041399 (Open Web Text)

Max Activating Token Index: 23

Text #2

Max Range: 5.2003. Min Range: -5.2003

Max Act: 5.1378. Min Act: -0.1700

Data Index: 4300412 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 5.2003. Min Range: -5.2003

Max Act: 5.1690. Min Act: -0.1700

Data Index: 8321994 (Open Web Text)

Max Activating Token Index: 14

Text #4

Max Range: 5.2003. Min Range: -5.2003

Max Act: 5.1378. Min Act: -0.1700

Data Index: 4492323 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.2003. Min Range: -5.2003

Max Act: 5.1378. Min Act: -0.1700

Data Index: 2941739 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 5.2003. Min Range: -5.2003

Max Act: 5.1065. Min Act: -0.1700

Data Index: 8647070 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 5.2003. Min Range: -5.2003

Max Act: 5.1065. Min Act: -0.1700

Data Index: 3938049 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.2003. Min Range: -5.2003

Max Act: 5.1378. Min Act: -0.1700

Data Index: 502966 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 5.2003. Min Range: -5.2003

Max Act: 5.1065. Min Act: -0.1700

Data Index: 878756 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 5.2003. Min Range: -5.2003

Max Act: 5.0440. Min Act: -0.1700

Data Index: 6536642 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 5.2003. Min Range: -5.2003

Max Act: 5.0440. Min Act: -0.1700

Data Index: 5316073 (Open Web Text)

Max Activating Token Index: 15

Text #12

Max Range: 5.2003. Min Range: -5.2003

Max Act: 5.0753. Min Act: -0.1700

Data Index: 1216189 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 5.2003. Min Range: -5.2003

Max Act: 5.0440. Min Act: -0.1700

Data Index: 1165989 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 5.2003. Min Range: -5.2003

Max Act: 5.0440. Min Act: -0.1700

Data Index: 4807522 (Open Web Text)

Max Activating Token Index: 20

Text #15

Max Range: 5.2003. Min Range: -5.2003

Max Act: 5.0440. Min Act: -0.1700

Data Index: 3338928 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 5.2003. Min Range: -5.2003

Max Act: 5.0128. Min Act: -0.1700

Data Index: 126583 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 5.2003. Min Range: -5.2003

Max Act: 5.0440. Min Act: -0.1700

Data Index: 16152 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 5.2003. Min Range: -5.2003

Max Act: 5.0440. Min Act: -0.1700

Data Index: 426523 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 5.2003. Min Range: -5.2003

Max Act: 5.0440. Min Act: -0.1700

Data Index: 4319893 (Open Web Text)

Max Activating Token Index: 3