Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2523 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3387. Min Range: -1.3387

Max Act: 1.3136. Min Act: -0.0000

Data Index: 627135 (The Pile)

Max Activating Token Index: 708

Text #1

Max Range: 1.3387. Min Range: -1.3387

Max Act: 1.2644. Min Act: -0.0000

Data Index: 431787 (The Pile)

Max Activating Token Index: 589

Text #2

Max Range: 1.3387. Min Range: -1.3387

Max Act: 1.2074. Min Act: -0.0000

Data Index: 1272842 (The Pile)

Max Activating Token Index: 641

Text #3

Max Range: 1.3387. Min Range: -1.3387

Max Act: 1.1973. Min Act: -0.0000

Data Index: 1606577 (The Pile)

Max Activating Token Index: 680

Text #4

Max Range: 1.3387. Min Range: -1.3387

Max Act: 1.2046. Min Act: -0.0000

Data Index: 579022 (The Pile)

Max Activating Token Index: 756

Text #5

Max Range: 1.3387. Min Range: -1.3387

Max Act: 1.3387. Min Act: -0.0000

Data Index: 945030 (The Pile)

Max Activating Token Index: 826

Text #6

Max Range: 1.3387. Min Range: -1.3387

Max Act: 1.2992. Min Act: -0.0000

Data Index: 281735 (The Pile)

Max Activating Token Index: 282

Text #7

Max Range: 1.3387. Min Range: -1.3387

Max Act: 1.2822. Min Act: -0.0000

Data Index: 849786 (The Pile)

Max Activating Token Index: 855

Text #8

Max Range: 1.3387. Min Range: -1.3387

Max Act: 1.0946. Min Act: -0.0000

Data Index: 1402615 (The Pile)

Max Activating Token Index: 542

Text #9

Max Range: 1.3387. Min Range: -1.3387

Max Act: 1.1245. Min Act: -0.0000

Data Index: 809088 (The Pile)

Max Activating Token Index: 209

Text #10

Max Range: 1.3387. Min Range: -1.3387

Max Act: 1.0679. Min Act: -0.0000

Data Index: 1350454 (The Pile)

Max Activating Token Index: 218

Text #11

Max Range: 1.3387. Min Range: -1.3387

Max Act: 1.1297. Min Act: -0.0000

Data Index: 833998 (The Pile)

Max Activating Token Index: 740

Text #12

Max Range: 1.3387. Min Range: -1.3387

Max Act: 1.1003. Min Act: -0.0000

Data Index: 1382972 (The Pile)

Max Activating Token Index: 218

Text #13

Max Range: 1.3387. Min Range: -1.3387

Max Act: 1.0662. Min Act: -0.0000

Data Index: 33825 (The Pile)

Max Activating Token Index: 40

Text #14

Max Range: 1.3387. Min Range: -1.3387

Max Act: 1.0963. Min Act: -0.0000

Data Index: 1139161 (The Pile)

Max Activating Token Index: 133

Text #15

Max Range: 1.3387. Min Range: -1.3387

Max Act: 1.0567. Min Act: -0.0000

Data Index: 416685 (The Pile)

Max Activating Token Index: 348

Text #16

Max Range: 1.3387. Min Range: -1.3387

Max Act: 1.0534. Min Act: -0.0000

Data Index: 575028 (The Pile)

Max Activating Token Index: 243

Text #17

Max Range: 1.3387. Min Range: -1.3387

Max Act: 0.9616. Min Act: -0.0000

Data Index: 868215 (The Pile)

Max Activating Token Index: 612

Text #18

Max Range: 1.3387. Min Range: -1.3387

Max Act: 1.0717. Min Act: -0.0000

Data Index: 235505 (The Pile)

Max Activating Token Index: 608

Text #19

Max Range: 1.3387. Min Range: -1.3387

Max Act: 0.9793. Min Act: -0.0001

Data Index: 1492760 (The Pile)

Max Activating Token Index: 794