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

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

Neuron 3741 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0387. Min Range: -2.0387

Max Act: 2.0387. Min Act: -0.0000

Data Index: 364562 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 2.0387. Min Range: -2.0387

Max Act: 1.6246. Min Act: -0.0000

Data Index: 105869 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 2.0387. Min Range: -2.0387

Max Act: 1.6721. Min Act: -0.0000

Data Index: 154162 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 2.0387. Min Range: -2.0387

Max Act: 1.6138. Min Act: -0.0000

Data Index: 1028822 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 2.0387. Min Range: -2.0387

Max Act: 1.5090. Min Act: -0.0000

Data Index: 396103 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 2.0387. Min Range: -2.0387

Max Act: 1.5051. Min Act: -0.0000

Data Index: 570148 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 2.0387. Min Range: -2.0387

Max Act: 1.5804. Min Act: -0.0000

Data Index: 103254 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 2.0387. Min Range: -2.0387

Max Act: 1.5584. Min Act: -0.0000

Data Index: 932188 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 2.0387. Min Range: -2.0387

Max Act: 1.5228. Min Act: -0.0000

Data Index: 540392 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 2.0387. Min Range: -2.0387

Max Act: 1.3585. Min Act: -0.0000

Data Index: 1206432 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 2.0387. Min Range: -2.0387

Max Act: 1.4333. Min Act: -0.0000

Data Index: 791576 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 2.0387. Min Range: -2.0387

Max Act: 1.5087. Min Act: -0.0000

Data Index: 326250 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 2.0387. Min Range: -2.0387

Max Act: 1.4143. Min Act: -0.0000

Data Index: 1075518 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 2.0387. Min Range: -2.0387

Max Act: 1.4838. Min Act: -0.0000

Data Index: 570523 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 2.0387. Min Range: -2.0387

Max Act: 1.4760. Min Act: -0.0000

Data Index: 639235 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 2.0387. Min Range: -2.0387

Max Act: 1.4843. Min Act: -0.0000

Data Index: 451614 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 2.0387. Min Range: -2.0387

Max Act: 1.4647. Min Act: -0.0000

Data Index: 995067 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 2.0387. Min Range: -2.0387

Max Act: 1.2998. Min Act: -0.0000

Data Index: 824168 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 2.0387. Min Range: -2.0387

Max Act: 1.3678. Min Act: -0.0000

Data Index: 876174 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 2.0387. Min Range: -2.0387

Max Act: 1.4489. Min Act: -0.0000

Data Index: 788559 (C4 (Web Text))

Max Activating Token Index: 475