Model: GELU Model: 2 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1512 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.2387. Min Range: -3.2387

Max Act: 3.2387. Min Act: -0.1700

Data Index: 1300837 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 3.2387. Min Range: -3.2387

Max Act: 3.2229. Min Act: -0.1700

Data Index: 456211 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 3.2387. Min Range: -3.2387

Max Act: 3.2072. Min Act: -0.1700

Data Index: 565203 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 3.2387. Min Range: -3.2387

Max Act: 3.2072. Min Act: -0.1700

Data Index: 167357 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 3.2387. Min Range: -3.2387

Max Act: 3.1757. Min Act: -0.1700

Data Index: 332481 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 3.2387. Min Range: -3.2387

Max Act: 3.1442. Min Act: -0.1700

Data Index: 735367 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 3.2387. Min Range: -3.2387

Max Act: 3.1600. Min Act: -0.1700

Data Index: 26820 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 3.2387. Min Range: -3.2387

Max Act: 3.1600. Min Act: -0.1700

Data Index: 1012994 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 3.2387. Min Range: -3.2387

Max Act: 3.1600. Min Act: -0.1700

Data Index: 902633 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 3.2387. Min Range: -3.2387

Max Act: 3.1285. Min Act: -0.1700

Data Index: 241370 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 3.2387. Min Range: -3.2387

Max Act: 3.1442. Min Act: -0.1700

Data Index: 343529 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 3.2387. Min Range: -3.2387

Max Act: 3.1442. Min Act: -0.1700

Data Index: 190086 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 3.2387. Min Range: -3.2387

Max Act: 3.1442. Min Act: -0.1700

Data Index: 377861 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 3.2387. Min Range: -3.2387

Max Act: 3.1442. Min Act: -0.1700

Data Index: 392930 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 3.2387. Min Range: -3.2387

Max Act: 3.1285. Min Act: -0.1700

Data Index: 1182971 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 3.2387. Min Range: -3.2387

Max Act: 3.1285. Min Act: -0.1700

Data Index: 31875 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 3.2387. Min Range: -3.2387

Max Act: 3.1285. Min Act: -0.1700

Data Index: 986468 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 3.2387. Min Range: -3.2387

Max Act: 3.1127. Min Act: -0.1700

Data Index: 50563 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 3.2387. Min Range: -3.2387

Max Act: 3.1127. Min Act: -0.1700

Data Index: 1287458 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 3.2387. Min Range: -3.2387

Max Act: 3.1127. Min Act: -0.1700

Data Index: 82665 (C4 (Web Text))

Max Activating Token Index: 21