Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4666 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.7387. Min Range: -2.7387

Max Act: 2.7387. Min Act: -0.0000

Data Index: 69546 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 2.7387. Min Range: -2.7387

Max Act: 2.1013. Min Act: -0.0000

Data Index: 662772 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 2.7387. Min Range: -2.7387

Max Act: 1.9097. Min Act: -0.0000

Data Index: 1011329 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 2.7387. Min Range: -2.7387

Max Act: 1.8675. Min Act: -0.0000

Data Index: 619780 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 2.7387. Min Range: -2.7387

Max Act: 1.7450. Min Act: -0.0000

Data Index: 153729 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 2.7387. Min Range: -2.7387

Max Act: 1.8209. Min Act: -0.0000

Data Index: 878014 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 2.7387. Min Range: -2.7387

Max Act: 1.6201. Min Act: -0.0000

Data Index: 201092 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 2.7387. Min Range: -2.7387

Max Act: 1.3584. Min Act: -0.0000

Data Index: 1254936 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 2.7387. Min Range: -2.7387

Max Act: 1.3395. Min Act: -0.0000

Data Index: 20826 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 2.7387. Min Range: -2.7387

Max Act: 1.3161. Min Act: -0.0000

Data Index: 244326 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 2.7387. Min Range: -2.7387

Max Act: 1.1827. Min Act: -0.0000

Data Index: 62828 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 2.7387. Min Range: -2.7387

Max Act: 1.0968. Min Act: -0.0000

Data Index: 1116954 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 2.7387. Min Range: -2.7387

Max Act: 1.2240. Min Act: -0.0000

Data Index: 961795 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 2.7387. Min Range: -2.7387

Max Act: 1.0616. Min Act: -0.0000

Data Index: 889733 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 2.7387. Min Range: -2.7387

Max Act: 1.0826. Min Act: -0.0000

Data Index: 87929 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 2.7387. Min Range: -2.7387

Max Act: 1.0024. Min Act: -0.0000

Data Index: 1345379 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 2.7387. Min Range: -2.7387

Max Act: 1.0505. Min Act: -0.0000

Data Index: 959987 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 2.7387. Min Range: -2.7387

Max Act: 0.9736. Min Act: -0.0000

Data Index: 594187 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 2.7387. Min Range: -2.7387

Max Act: 0.9711. Min Act: -0.0000

Data Index: 137523 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 2.7387. Min Range: -2.7387

Max Act: 0.9366. Min Act: -0.0000

Data Index: 94579 (C4 (Web Text))

Max Activating Token Index: 160