Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3796 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0860. Min Act: -0.0003

Data Index: 617074 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0809. Min Act: -0.0003

Data Index: 984261 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0768. Min Act: -0.0003

Data Index: 1053246 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0748. Min Act: -0.0003

Data Index: 577678 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0721. Min Act: -0.0003

Data Index: 833497 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0743. Min Act: -0.0003

Data Index: 500132 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0743. Min Act: -0.0003

Data Index: 688956 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0688. Min Act: -0.0003

Data Index: 510215 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0738. Min Act: -0.0003

Data Index: 1185741 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0709. Min Act: -0.0003

Data Index: 1260472 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0683. Min Act: -0.0003

Data Index: 284490 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0705. Min Act: -0.0003

Data Index: 501595 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0678. Min Act: -0.0003

Data Index: 969530 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0714. Min Act: -0.0003

Data Index: 427003 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0654. Min Act: -0.0003

Data Index: 256577 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0709. Min Act: -0.0003

Data Index: 800002 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0706. Min Act: -0.0003

Data Index: 51759 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0705. Min Act: -0.0003

Data Index: 398038 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0729. Min Act: -0.0003

Data Index: 1266029 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0669. Min Act: -0.0003

Data Index: 455281 (C4 (Web Text))

Max Activating Token Index: 108