Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1514 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0985. Min Act: -0.0002

Data Index: 633985 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0885. Min Act: -0.0002

Data Index: 1156027 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0887. Min Act: -0.0002

Data Index: 420199 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0897. Min Act: -0.0001

Data Index: 1286003 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0816. Min Act: -0.0002

Data Index: 890193 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0812. Min Act: -0.0001

Data Index: 17103 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0793. Min Act: -0.0002

Data Index: 114600 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1101039 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1178865 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0785. Min Act: -0.0000

Data Index: 428754 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0790. Min Act: -0.0001

Data Index: 127869 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0790. Min Act: -0.0002

Data Index: 193960 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0793. Min Act: -0.0002

Data Index: 874605 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0798. Min Act: -0.0000

Data Index: 1278035 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1300073 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0778. Min Act: -0.0002

Data Index: 148062 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0765. Min Act: -0.0002

Data Index: 132762 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0771. Min Act: -0.0002

Data Index: 123208 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0785. Min Act: -0.0001

Data Index: 547713 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0748. Min Act: -0.0002

Data Index: 717038 (C4 (Web Text))

Max Activating Token Index: 19