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

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

Neuron 4904 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.3387. Min Act: -0.0000

Data Index: 281855 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.3082. Min Act: -0.0000

Data Index: 360694 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2443. Min Act: -0.0000

Data Index: 698662 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2355. Min Act: -0.0000

Data Index: 291195 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2377. Min Act: -0.0000

Data Index: 656081 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2205. Min Act: -0.0000

Data Index: 500195 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2080. Min Act: -0.0000

Data Index: 57085 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.1964. Min Act: -0.0000

Data Index: 1099677 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2069. Min Act: -0.0000

Data Index: 277433 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.1700. Min Act: -0.0000

Data Index: 878589 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.1865. Min Act: -0.0000

Data Index: 470018 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.1745. Min Act: -0.0000

Data Index: 571810 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.1564. Min Act: -0.0000

Data Index: 435143 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.1778. Min Act: -0.0000

Data Index: 1154499 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.1687. Min Act: -0.0000

Data Index: 9446 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.1760. Min Act: -0.0000

Data Index: 389510 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1113559 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.1639. Min Act: -0.0000

Data Index: 1088070 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.1815. Min Act: -0.0000

Data Index: 426902 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.1680. Min Act: -0.0000

Data Index: 956933 (C4 (Web Text))

Max Activating Token Index: 491