Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 693 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1150. Min Act: -0.0003

Data Index: 53760 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1151. Min Act: -0.0003

Data Index: 524594 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1153. Min Act: -0.0003

Data Index: 376124 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1036. Min Act: -0.0003

Data Index: 395989 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1071. Min Act: -0.0004

Data Index: 502099 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1108. Min Act: -0.0003

Data Index: 277024 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0977. Min Act: -0.0003

Data Index: 1070 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0966. Min Act: -0.0003

Data Index: 1114566 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1014. Min Act: -0.0003

Data Index: 445792 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1001. Min Act: -0.0003

Data Index: 576861 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0960. Min Act: -0.0003

Data Index: 263667 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1003. Min Act: -0.0003

Data Index: 467001 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0978. Min Act: -0.0003

Data Index: 706464 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0907. Min Act: -0.0003

Data Index: 1061556 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0966. Min Act: -0.0003

Data Index: 498845 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0942. Min Act: -0.0003

Data Index: 18937 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0938. Min Act: -0.0003

Data Index: 136896 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0919. Min Act: -0.0003

Data Index: 331986 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0910. Min Act: -0.0003

Data Index: 445491 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0903. Min Act: -0.0003

Data Index: 671946 (C4 (Web Text))

Max Activating Token Index: 530