Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1215 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.5387. Min Act: -0.0000

Data Index: 424813 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.4968. Min Act: -0.0000

Data Index: 323932 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.3367. Min Act: -0.0000

Data Index: 682956 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.3339. Min Act: -0.0000

Data Index: 899751 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.3370. Min Act: -0.0000

Data Index: 753073 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.3683. Min Act: -0.0000

Data Index: 430976 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.2048. Min Act: -0.0000

Data Index: 829077 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.2295. Min Act: -0.0000

Data Index: 464712 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.1402. Min Act: -0.0000

Data Index: 473909 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.1500. Min Act: -0.0000

Data Index: 423823 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.2222. Min Act: -0.0000

Data Index: 500600 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.2291. Min Act: -0.0000

Data Index: 1076872 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.1129. Min Act: -0.0000

Data Index: 31983 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.1717. Min Act: -0.0000

Data Index: 1058821 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.1774. Min Act: -0.0000

Data Index: 1081619 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.1477. Min Act: -0.0000

Data Index: 172006 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.1258. Min Act: -0.0000

Data Index: 1092958 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.1370. Min Act: -0.0000

Data Index: 644739 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.2196. Min Act: -0.0000

Data Index: 93162 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.0530. Min Act: -0.0000

Data Index: 722204 (C4 (Web Text))

Max Activating Token Index: 570