Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1069 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.7387. Min Range: -5.7387

Max Act: 5.7387. Min Act: -0.1700

Data Index: 550657 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 5.7387. Min Range: -5.7387

Max Act: 5.6762. Min Act: -0.1700

Data Index: 664783 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 5.7387. Min Range: -5.7387

Max Act: 5.4262. Min Act: -0.1700

Data Index: 948358 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 5.7387. Min Range: -5.7387

Max Act: 5.3012. Min Act: -0.1700

Data Index: 1307613 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 5.7387. Min Range: -5.7387

Max Act: 5.3012. Min Act: -0.1700

Data Index: 219116 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 5.7387. Min Range: -5.7387

Max Act: 5.3637. Min Act: -0.1700

Data Index: 436160 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 5.7387. Min Range: -5.7387

Max Act: 5.3324. Min Act: -0.1700

Data Index: 965388 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 5.7387. Min Range: -5.7387

Max Act: 5.3637. Min Act: -0.1700

Data Index: 1275427 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 5.7387. Min Range: -5.7387

Max Act: 5.3637. Min Act: -0.1700

Data Index: 285597 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 5.7387. Min Range: -5.7387

Max Act: 5.2699. Min Act: -0.1700

Data Index: 698354 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 5.7387. Min Range: -5.7387

Max Act: 5.1762. Min Act: -0.1700

Data Index: 536046 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 5.7387. Min Range: -5.7387

Max Act: 5.2699. Min Act: -0.1700

Data Index: 330923 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 5.7387. Min Range: -5.7387

Max Act: 5.0824. Min Act: -0.1700

Data Index: 150570 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 5.7387. Min Range: -5.7387

Max Act: 5.1762. Min Act: -0.1700

Data Index: 54637 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 5.7387. Min Range: -5.7387

Max Act: 5.0512. Min Act: -0.1700

Data Index: 1354867 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 5.7387. Min Range: -5.7387

Max Act: 5.0512. Min Act: -0.1700

Data Index: 767290 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 5.7387. Min Range: -5.7387

Max Act: 5.0512. Min Act: -0.1700

Data Index: 402018 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 5.7387. Min Range: -5.7387

Max Act: 4.9262. Min Act: -0.1700

Data Index: 1166567 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 5.7387. Min Range: -5.7387

Max Act: 5.0199. Min Act: -0.1700

Data Index: 1239266 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 5.7387. Min Range: -5.7387

Max Act: 5.0512. Min Act: -0.1700

Data Index: 1279408 (C4 (Web Text))

Max Activating Token Index: 408