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

Dataset: Open Web Text

Neuron 1124 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: 3.9387. Min Range: -3.9387

Max Act: 3.9156. Min Act: -0.1700

Data Index: 552698 (Open Web Text)

Max Activating Token Index: 475

Text #1

Max Range: 3.9387. Min Range: -3.9387

Max Act: 3.9209. Min Act: -0.1700

Data Index: 2587851 (Open Web Text)

Max Activating Token Index: 101

Text #2

Max Range: 3.9387. Min Range: -3.9387

Max Act: 3.9387. Min Act: -0.1700

Data Index: 6566173 (Open Web Text)

Max Activating Token Index: 443

Text #3

Max Range: 3.9387. Min Range: -3.9387

Max Act: 3.9001. Min Act: -0.1700

Data Index: 634577 (Open Web Text)

Max Activating Token Index: 565

Text #4

Max Range: 3.9387. Min Range: -3.9387

Max Act: 3.9056. Min Act: -0.1700

Data Index: 1646555 (Open Web Text)

Max Activating Token Index: 407

Text #5

Max Range: 3.9387. Min Range: -3.9387

Max Act: 3.9009. Min Act: -0.1700

Data Index: 1172207 (Open Web Text)

Max Activating Token Index: 63

Text #6

Max Range: 3.9387. Min Range: -3.9387

Max Act: 3.8988. Min Act: -0.1700

Data Index: 2380972 (Open Web Text)

Max Activating Token Index: 490

Text #7

Max Range: 3.9387. Min Range: -3.9387

Max Act: 3.8857. Min Act: -0.1700

Data Index: 6391375 (Open Web Text)

Max Activating Token Index: 166

Text #8

Max Range: 3.9387. Min Range: -3.9387

Max Act: 3.8963. Min Act: -0.1700

Data Index: 6345803 (Open Web Text)

Max Activating Token Index: 673

Text #9

Max Range: 3.9387. Min Range: -3.9387

Max Act: 3.8570. Min Act: -0.1700

Data Index: 6379780 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.9387. Min Range: -3.9387

Max Act: 3.8499. Min Act: -0.1700

Data Index: 6237716 (Open Web Text)

Max Activating Token Index: 539

Text #11

Max Range: 3.9387. Min Range: -3.9387

Max Act: 3.8459. Min Act: -0.1700

Data Index: 1652731 (Open Web Text)

Max Activating Token Index: 447

Text #12

Max Range: 3.9387. Min Range: -3.9387

Max Act: 3.8547. Min Act: -0.1700

Data Index: 5636427 (Open Web Text)

Max Activating Token Index: 639

Text #13

Max Range: 3.9387. Min Range: -3.9387

Max Act: 3.8789. Min Act: -0.1700

Data Index: 5033357 (Open Web Text)

Max Activating Token Index: 627

Text #14

Max Range: 3.9387. Min Range: -3.9387

Max Act: 3.8644. Min Act: -0.1700

Data Index: 6778801 (Open Web Text)

Max Activating Token Index: 167

Text #15

Max Range: 3.9387. Min Range: -3.9387

Max Act: 3.8513. Min Act: -0.1700

Data Index: 2624582 (Open Web Text)

Max Activating Token Index: 417

Text #16

Max Range: 3.9387. Min Range: -3.9387

Max Act: 3.8849. Min Act: -0.1700

Data Index: 8348281 (Open Web Text)

Max Activating Token Index: 1018

Text #17

Max Range: 3.9387. Min Range: -3.9387

Max Act: 3.8591. Min Act: -0.1700

Data Index: 804061 (Open Web Text)

Max Activating Token Index: 350

Text #18

Max Range: 3.9387. Min Range: -3.9387

Max Act: 3.8668. Min Act: -0.1700

Data Index: 3050838 (Open Web Text)

Max Activating Token Index: 112

Text #19

Max Range: 3.9387. Min Range: -3.9387

Max Act: 3.8589. Min Act: -0.1700

Data Index: 4733947 (Open Web Text)

Max Activating Token Index: 111