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

Dataset: Open Web Text

Neuron 426 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: 1.5387. Min Range: -1.5387

Max Act: 1.5387. Min Act: -0.1700

Data Index: 6791968 (Open Web Text)

Max Activating Token Index: 646

Text #1

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.5153. Min Act: -0.1700

Data Index: 1983591 (Open Web Text)

Max Activating Token Index: 444

Text #2

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.5090. Min Act: -0.1700

Data Index: 6216245 (Open Web Text)

Max Activating Token Index: 64

Text #3

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.5101. Min Act: -0.1700

Data Index: 4632919 (Open Web Text)

Max Activating Token Index: 560

Text #4

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.5104. Min Act: -0.1693

Data Index: 7892314 (Open Web Text)

Max Activating Token Index: 53

Text #5

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.4916. Min Act: -0.1698

Data Index: 4632920 (Open Web Text)

Max Activating Token Index: 146

Text #6

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.4872. Min Act: -0.1700

Data Index: 1806507 (Open Web Text)

Max Activating Token Index: 243

Text #7

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.4787. Min Act: -0.1700

Data Index: 8476722 (Open Web Text)

Max Activating Token Index: 756

Text #8

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.4735. Min Act: -0.1700

Data Index: 7655980 (Open Web Text)

Max Activating Token Index: 442

Text #9

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.4788. Min Act: -0.1700

Data Index: 8542698 (Open Web Text)

Max Activating Token Index: 494

Text #10

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.4760. Min Act: -0.1700

Data Index: 535970 (Open Web Text)

Max Activating Token Index: 145

Text #11

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.4621. Min Act: -0.1700

Data Index: 6227999 (Open Web Text)

Max Activating Token Index: 974

Text #12

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.4577. Min Act: -0.1699

Data Index: 3284334 (Open Web Text)

Max Activating Token Index: 476

Text #13

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.4626. Min Act: -0.1700

Data Index: 4110227 (Open Web Text)

Max Activating Token Index: 115

Text #14

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.4574. Min Act: -0.1700

Data Index: 8437130 (Open Web Text)

Max Activating Token Index: 529

Text #15

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.4618. Min Act: -0.1699

Data Index: 5963812 (Open Web Text)

Max Activating Token Index: 332

Text #16

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.4705. Min Act: -0.1700

Data Index: 3627437 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.4612. Min Act: -0.1700

Data Index: 2188603 (Open Web Text)

Max Activating Token Index: 107

Text #18

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.4512. Min Act: -0.1700

Data Index: 6434296 (Open Web Text)

Max Activating Token Index: 148

Text #19

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.4574. Min Act: -0.1700

Data Index: 94554 (Open Web Text)

Max Activating Token Index: 577