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

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

Neuron 5432 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1186541 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1034173 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0685. Min Act: -0.0002

Data Index: 1134691 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0649. Min Act: -0.0002

Data Index: 915221 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0641. Min Act: -0.0002

Data Index: 525748 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0609. Min Act: -0.0002

Data Index: 484392 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1165974 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0603. Min Act: -0.0002

Data Index: 142402 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0602. Min Act: -0.0002

Data Index: 472293 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1301022 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0591. Min Act: -0.0002

Data Index: 226114 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0571. Min Act: -0.0002

Data Index: 408053 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0558. Min Act: -0.0002

Data Index: 640036 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0544. Min Act: -0.0002

Data Index: 632073 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1035421 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0538. Min Act: -0.0002

Data Index: 419428 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0568. Min Act: -0.0002

Data Index: 618634 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0545. Min Act: -0.0002

Data Index: 496664 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1342670 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1236891 (C4 (Web Text))

Max Activating Token Index: 469