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

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

Neuron 2564 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3387. Min Range: -3.3387

Max Act: 3.3387. Min Act: -0.0000

Data Index: 880165 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 3.3387. Min Range: -3.3387

Max Act: 2.7930. Min Act: -0.0000

Data Index: 1224625 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 3.3387. Min Range: -3.3387

Max Act: 2.7349. Min Act: -0.0000

Data Index: 356876 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 3.3387. Min Range: -3.3387

Max Act: 2.7558. Min Act: -0.0000

Data Index: 1313957 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 3.3387. Min Range: -3.3387

Max Act: 2.7546. Min Act: -0.0000

Data Index: 1349062 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 3.3387. Min Range: -3.3387

Max Act: 2.1860. Min Act: -0.0000

Data Index: 82333 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 3.3387. Min Range: -3.3387

Max Act: 2.3806. Min Act: -0.0000

Data Index: 131143 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 3.3387. Min Range: -3.3387

Max Act: 2.5071. Min Act: -0.0000

Data Index: 51713 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 3.3387. Min Range: -3.3387

Max Act: 2.4898. Min Act: -0.0000

Data Index: 75518 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 3.3387. Min Range: -3.3387

Max Act: 2.3187. Min Act: -0.0000

Data Index: 1116212 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 3.3387. Min Range: -3.3387

Max Act: 2.3117. Min Act: -0.0000

Data Index: 936446 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 3.3387. Min Range: -3.3387

Max Act: 2.2949. Min Act: -0.0000

Data Index: 55022 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 3.3387. Min Range: -3.3387

Max Act: 2.1390. Min Act: -0.0000

Data Index: 1083880 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 3.3387. Min Range: -3.3387

Max Act: 2.0341. Min Act: -0.0000

Data Index: 509152 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 3.3387. Min Range: -3.3387

Max Act: 2.0943. Min Act: -0.0000

Data Index: 1083955 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 3.3387. Min Range: -3.3387

Max Act: 1.9649. Min Act: -0.0000

Data Index: 90771 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 3.3387. Min Range: -3.3387

Max Act: 2.1753. Min Act: -0.0000

Data Index: 651638 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 3.3387. Min Range: -3.3387

Max Act: 1.9590. Min Act: -0.0000

Data Index: 177748 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 3.3387. Min Range: -3.3387

Max Act: 2.0572. Min Act: -0.0000

Data Index: 905386 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 3.3387. Min Range: -3.3387

Max Act: 2.0602. Min Act: -0.0000

Data Index: 784339 (C4 (Web Text))

Max Activating Token Index: 118