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

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

Neuron 1901 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: 0.0864. Min Range: -0.0864

Max Act: 0.0844. Min Act: -0.0003

Data Index: 182925 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0864. Min Act: -0.0003

Data Index: 313204 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0783. Min Act: -0.0003

Data Index: 121391 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0784. Min Act: -0.0003

Data Index: 702349 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0749. Min Act: -0.0003

Data Index: 887731 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0743. Min Act: -0.0003

Data Index: 988006 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0752. Min Act: -0.0003

Data Index: 1011211 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0706. Min Act: -0.0003

Data Index: 860965 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0697. Min Act: -0.0003

Data Index: 54121 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0679. Min Act: -0.0003

Data Index: 751268 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0678. Min Act: -0.0003

Data Index: 293259 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0699. Min Act: -0.0003

Data Index: 1136435 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0655. Min Act: -0.0002

Data Index: 751549 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0646. Min Act: -0.0002

Data Index: 223146 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0668. Min Act: -0.0003

Data Index: 1333662 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0650. Min Act: -0.0003

Data Index: 235957 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0649. Min Act: -0.0003

Data Index: 743262 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0652. Min Act: -0.0003

Data Index: 553234 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0649. Min Act: -0.0003

Data Index: 162795 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0619. Min Act: -0.0003

Data Index: 1203859 (C4 (Web Text))

Max Activating Token Index: 668