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

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

Neuron 300 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1200. Min Act: -0.0006

Data Index: 866819 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0997. Min Act: -0.0006

Data Index: 827868 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0955. Min Act: -0.0006

Data Index: 318712 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0867. Min Act: -0.0006

Data Index: 143745 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0898. Min Act: -0.0006

Data Index: 859169 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0885. Min Act: -0.0006

Data Index: 925186 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0840. Min Act: -0.0006

Data Index: 417623 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0861. Min Act: -0.0005

Data Index: 506267 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0848. Min Act: -0.0006

Data Index: 1226064 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0804. Min Act: -0.0006

Data Index: 716762 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0835. Min Act: -0.0006

Data Index: 395914 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0799. Min Act: -0.0006

Data Index: 435394 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0832. Min Act: -0.0006

Data Index: 1086404 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0797. Min Act: -0.0006

Data Index: 722050 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0864. Min Act: -0.0006

Data Index: 1094641 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0858. Min Act: -0.0006

Data Index: 71301 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0856. Min Act: -0.0006

Data Index: 66874 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0819. Min Act: -0.0006

Data Index: 486298 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0814. Min Act: -0.0006

Data Index: 893912 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0843. Min Act: -0.0006

Data Index: 208013 (C4 (Web Text))

Max Activating Token Index: 142