Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2042 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1178. Min Act: -0.0003

Data Index: 472602 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1049. Min Act: -0.0003

Data Index: 60748 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0986. Min Act: -0.0003

Data Index: 290759 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0935. Min Act: -0.0003

Data Index: 180584 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1044. Min Act: -0.0003

Data Index: 938613 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0972. Min Act: -0.0003

Data Index: 143963 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1037. Min Act: -0.0003

Data Index: 1100686 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0991. Min Act: -0.0003

Data Index: 530972 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0952. Min Act: -0.0003

Data Index: 136274 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1032. Min Act: -0.0003

Data Index: 752338 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1019. Min Act: -0.0003

Data Index: 376110 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1013. Min Act: -0.0003

Data Index: 891783 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1008. Min Act: -0.0003

Data Index: 1011392 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1003. Min Act: -0.0003

Data Index: 1337747 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0994. Min Act: -0.0003

Data Index: 1255266 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0992. Min Act: -0.0003

Data Index: 365772 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1015. Min Act: -0.0003

Data Index: 1153950 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1020. Min Act: -0.0003

Data Index: 100137 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0982. Min Act: -0.0003

Data Index: 388351 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0907. Min Act: -0.0003

Data Index: 452823 (C4 (Web Text))

Max Activating Token Index: 46