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

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

Neuron 739 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4185. Min Act: -0.0002

Data Index: 683937 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4041. Min Act: -0.0003

Data Index: 1313958 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4289. Min Act: -0.0002

Data Index: 708808 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4154. Min Act: -0.0002

Data Index: 1003533 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4038. Min Act: -0.0002

Data Index: 1127352 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4082. Min Act: -0.0002

Data Index: 474831 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4025. Min Act: -0.0002

Data Index: 1288414 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4118. Min Act: -0.0003

Data Index: 932400 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4018. Min Act: -0.0002

Data Index: 753597 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4018. Min Act: -0.0003

Data Index: 258650 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.3941. Min Act: -0.0002

Data Index: 398739 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.3887. Min Act: -0.0002

Data Index: 1183278 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4001. Min Act: -0.0002

Data Index: 733535 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4020. Min Act: -0.0002

Data Index: 113411 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.3880. Min Act: -0.0002

Data Index: 1150015 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4007. Min Act: -0.0003

Data Index: 342678 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.3847. Min Act: -0.0003

Data Index: 1005083 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4057. Min Act: -0.0002

Data Index: 284239 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.3968. Min Act: -0.0002

Data Index: 535798 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.3840. Min Act: -0.0002

Data Index: 571940 (C4 (Web Text))

Max Activating Token Index: 16