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

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

Neuron 1884 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0827. Min Act: -0.0002

Data Index: 611907 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0812. Min Act: -0.0002

Data Index: 281401 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0761. Min Act: -0.0002

Data Index: 367065 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0764. Min Act: -0.0002

Data Index: 361000 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1569798 (Python Code)

Max Activating Token Index: 280

Text #5

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0736. Min Act: -0.0002

Data Index: 828614 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0780. Min Act: -0.0002

Data Index: 279936 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0761. Min Act: -0.0002

Data Index: 143422 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0792. Min Act: -0.0002

Data Index: 260417 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0780. Min Act: -0.0002

Data Index: 283662 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0811. Min Act: -0.0002

Data Index: 828167 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0669. Min Act: -0.0002

Data Index: 1182030 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0636. Min Act: -0.0002

Data Index: 153888 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0715. Min Act: -0.0002

Data Index: 465617 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0718. Min Act: -0.0002

Data Index: 587832 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0696. Min Act: -0.0002

Data Index: 689028 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0740. Min Act: -0.0002

Data Index: 120341 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0711. Min Act: -0.0002

Data Index: 31497 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0692. Min Act: -0.0002

Data Index: 1166424 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0714. Min Act: -0.0002

Data Index: 1086093 (C4 (Web Text))

Max Activating Token Index: 61