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

Dataset: Open Web Text

Neuron 2978 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: 3.0387. Min Range: -3.0387

Max Act: 3.0387. Min Act: -0.1700

Data Index: 6882719 (Open Web Text)

Max Activating Token Index: 58

Text #1

Max Range: 3.0387. Min Range: -3.0387

Max Act: 3.0268. Min Act: -0.1700

Data Index: 8559483 (Open Web Text)

Max Activating Token Index: 804

Text #2

Max Range: 3.0387. Min Range: -3.0387

Max Act: 3.0106. Min Act: -0.1700

Data Index: 2635963 (Open Web Text)

Max Activating Token Index: 456

Text #3

Max Range: 3.0387. Min Range: -3.0387

Max Act: 3.0032. Min Act: -0.1700

Data Index: 5289583 (Open Web Text)

Max Activating Token Index: 789

Text #4

Max Range: 3.0387. Min Range: -3.0387

Max Act: 3.0061. Min Act: -0.1700

Data Index: 4092417 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.0387. Min Range: -3.0387

Max Act: 3.0137. Min Act: -0.1700

Data Index: 3621526 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.0387. Min Range: -3.0387

Max Act: 3.0185. Min Act: -0.1700

Data Index: 6553540 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.0387. Min Range: -3.0387

Max Act: 3.0060. Min Act: -0.1700

Data Index: 2502683 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.0387. Min Range: -3.0387

Max Act: 3.0060. Min Act: -0.1700

Data Index: 2186448 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.0387. Min Range: -3.0387

Max Act: 3.0002. Min Act: -0.1700

Data Index: 7317901 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.0387. Min Range: -3.0387

Max Act: 3.0042. Min Act: -0.1700

Data Index: 3129252 (Open Web Text)

Max Activating Token Index: 51

Text #11

Max Range: 3.0387. Min Range: -3.0387

Max Act: 2.9954. Min Act: -0.1700

Data Index: 4266763 (Open Web Text)

Max Activating Token Index: 481

Text #12

Max Range: 3.0387. Min Range: -3.0387

Max Act: 2.9874. Min Act: -0.1700

Data Index: 6976138 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.0387. Min Range: -3.0387

Max Act: 2.9894. Min Act: -0.1700

Data Index: 6419913 (Open Web Text)

Max Activating Token Index: 49

Text #14

Max Range: 3.0387. Min Range: -3.0387

Max Act: 2.9794. Min Act: -0.1700

Data Index: 5853677 (Open Web Text)

Max Activating Token Index: 958

Text #15

Max Range: 3.0387. Min Range: -3.0387

Max Act: 2.9679. Min Act: -0.1700

Data Index: 3912907 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.0387. Min Range: -3.0387

Max Act: 2.9617. Min Act: -0.1700

Data Index: 3633172 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.0387. Min Range: -3.0387

Max Act: 2.9776. Min Act: -0.1700

Data Index: 3048968 (Open Web Text)

Max Activating Token Index: 65

Text #18

Max Range: 3.0387. Min Range: -3.0387

Max Act: 2.9642. Min Act: -0.1700

Data Index: 3833620 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.0387. Min Range: -3.0387

Max Act: 2.9700. Min Act: -0.1700

Data Index: 1670731 (Open Web Text)

Max Activating Token Index: 723