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

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

Neuron 1118 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1006. Min Act: -0.0005

Data Index: 1356966 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1029. Min Act: -0.0005

Data Index: 1031849 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1005. Min Act: -0.0005

Data Index: 562602 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1016. Min Act: -0.0005

Data Index: 51392 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0997. Min Act: -0.0005

Data Index: 1130338 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1066. Min Act: -0.0005

Data Index: 1072575 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1038. Min Act: -0.0005

Data Index: 562682 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0992. Min Act: -0.0005

Data Index: 584121 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1009. Min Act: -0.0005

Data Index: 186601 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1003. Min Act: -0.0005

Data Index: 1249026 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0963. Min Act: -0.0005

Data Index: 389878 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1029. Min Act: -0.0005

Data Index: 512683 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1011. Min Act: -0.0005

Data Index: 874110 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0994. Min Act: -0.0005

Data Index: 153674 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1008. Min Act: -0.0005

Data Index: 580176 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1006. Min Act: -0.0005

Data Index: 450429 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1001. Min Act: -0.0005

Data Index: 1049712 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0985. Min Act: -0.0005

Data Index: 1167831 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1018. Min Act: -0.0005

Data Index: 500772 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0995. Min Act: -0.0005

Data Index: 346768 (C4 (Web Text))

Max Activating Token Index: 215