Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 254 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1387. Min Range: -3.1387

Max Act: 3.1387. Min Act: -0.1700

Data Index: 944237 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 3.1387. Min Range: -3.1387

Max Act: 3.1071. Min Act: -0.1700

Data Index: 1240983 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 3.1387. Min Range: -3.1387

Max Act: 3.1071. Min Act: -0.1700

Data Index: 250649 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 3.1387. Min Range: -3.1387

Max Act: 3.0914. Min Act: -0.1700

Data Index: 11482 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 3.1387. Min Range: -3.1387

Max Act: 3.0914. Min Act: -0.1700

Data Index: 649545 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 3.1387. Min Range: -3.1387

Max Act: 3.0914. Min Act: -0.1700

Data Index: 1301653 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 3.1387. Min Range: -3.1387

Max Act: 3.0756. Min Act: -0.1700

Data Index: 296929 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 3.1387. Min Range: -3.1387

Max Act: 3.0756. Min Act: -0.1700

Data Index: 1265183 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 3.1387. Min Range: -3.1387

Max Act: 3.0598. Min Act: -0.1700

Data Index: 866718 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 3.1387. Min Range: -3.1387

Max Act: 3.0598. Min Act: -0.1700

Data Index: 379315 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 3.1387. Min Range: -3.1387

Max Act: 3.0440. Min Act: -0.1700

Data Index: 297991 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 3.1387. Min Range: -3.1387

Max Act: 3.0440. Min Act: -0.1700

Data Index: 564629 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 3.1387. Min Range: -3.1387

Max Act: 3.0124. Min Act: -0.1700

Data Index: 831365 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 3.1387. Min Range: -3.1387

Max Act: 3.0124. Min Act: -0.1700

Data Index: 365641 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 3.1387. Min Range: -3.1387

Max Act: 2.9966. Min Act: -0.1700

Data Index: 981077 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 3.1387. Min Range: -3.1387

Max Act: 2.9808. Min Act: -0.1700

Data Index: 1348630 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 3.1387. Min Range: -3.1387

Max Act: 2.9966. Min Act: -0.1700

Data Index: 247241 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 3.1387. Min Range: -3.1387

Max Act: 2.9808. Min Act: -0.1700

Data Index: 1091286 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 3.1387. Min Range: -3.1387

Max Act: 2.9808. Min Act: -0.1700

Data Index: 753537 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 3.1387. Min Range: -3.1387

Max Act: 2.9492. Min Act: -0.1700

Data Index: 564302 (C4 (Web Text))

Max Activating Token Index: 119