Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 75 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1187. Min Act: -0.0002

Data Index: 1237408 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1171. Min Act: -0.0002

Data Index: 741564 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1027. Min Act: -0.0002

Data Index: 68673 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0955. Min Act: -0.0002

Data Index: 1025882 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0946. Min Act: -0.0002

Data Index: 807890 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0958. Min Act: -0.0002

Data Index: 1051439 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0919. Min Act: -0.0002

Data Index: 866211 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0822. Min Act: -0.0002

Data Index: 156295 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0736. Min Act: -0.0002

Data Index: 1028877 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0769. Min Act: -0.0002

Data Index: 975917 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0766. Min Act: -0.0002

Data Index: 520838 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0761. Min Act: -0.0002

Data Index: 59950 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0780. Min Act: -0.0002

Data Index: 134559 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0708. Min Act: -0.0002

Data Index: 13128 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0704. Min Act: -0.0002

Data Index: 348794 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0721. Min Act: -0.0002

Data Index: 912791 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1264369 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0699. Min Act: -0.0002

Data Index: 668792 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0692. Min Act: -0.0002

Data Index: 605179 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0679. Min Act: -0.0002

Data Index: 318075 (C4 (Web Text))

Max Activating Token Index: 194