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

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

Neuron 1082 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2641. Min Act: -0.0000

Data Index: 892497 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2027. Min Act: -0.0000

Data Index: 126108 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1810. Min Act: -0.0000

Data Index: 50124 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1888. Min Act: -0.0000

Data Index: 836340 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1791. Min Act: -0.0000

Data Index: 887495 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1796. Min Act: -0.0000

Data Index: 554525 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1788. Min Act: -0.0000

Data Index: 236094 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1832. Min Act: -0.0000

Data Index: 581877 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1832. Min Act: -0.0000

Data Index: 394626 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1730. Min Act: -0.0000

Data Index: 248298 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1660. Min Act: -0.0000

Data Index: 291941 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1265164 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1762. Min Act: -0.0000

Data Index: 664761 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1680. Min Act: -0.0000

Data Index: 559582 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1691. Min Act: -0.0000

Data Index: 207627 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1747. Min Act: -0.0000

Data Index: 396373 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1660. Min Act: -0.0000

Data Index: 323473 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1574. Min Act: -0.0000

Data Index: 806609 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1575. Min Act: -0.0000

Data Index: 110715 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1560. Min Act: -0.0000

Data Index: 522852 (C4 (Web Text))

Max Activating Token Index: 44