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

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

Neuron 1065 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.9387. Min Act: -0.0000

Data Index: 1077571 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1186718 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1050432 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.7659. Min Act: -0.0000

Data Index: 1347009 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.6836. Min Act: -0.0000

Data Index: 48692 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.6535. Min Act: -0.0000

Data Index: 665627 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.6649. Min Act: -0.0000

Data Index: 290671 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.6264. Min Act: -0.0000

Data Index: 886810 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.5880. Min Act: -0.0000

Data Index: 152830 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.5846. Min Act: -0.0000

Data Index: 587757 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.6242. Min Act: -0.0000

Data Index: 890538 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.6218. Min Act: -0.0000

Data Index: 1358567 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.6288. Min Act: -0.0000

Data Index: 960584 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.5517. Min Act: -0.0000

Data Index: 1301438 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.5813. Min Act: -0.0000

Data Index: 1270962 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.5525. Min Act: -0.0000

Data Index: 117821 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.5187. Min Act: -0.0000

Data Index: 66748 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.5406. Min Act: -0.0000

Data Index: 1031463 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.5176. Min Act: -0.0000

Data Index: 35974 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.9387. Min Range: -0.9387

Max Act: 0.5151. Min Act: -0.0000

Data Index: 86049 (C4 (Web Text))

Max Activating Token Index: 417