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

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

Neuron 587 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: 0.0864. Min Range: -0.0864

Max Act: 0.0847. Min Act: -0.0003

Data Index: 976557 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0864. Min Act: -0.0003

Data Index: 853649 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0798. Min Act: -0.0003

Data Index: 6909 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0813. Min Act: -0.0003

Data Index: 109226 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0778. Min Act: -0.0003

Data Index: 873720 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0772. Min Act: -0.0003

Data Index: 639894 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0751. Min Act: -0.0003

Data Index: 1147177 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0747. Min Act: -0.0003

Data Index: 1158343 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0724. Min Act: -0.0003

Data Index: 1151749 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0694. Min Act: -0.0003

Data Index: 972430 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0691. Min Act: -0.0003

Data Index: 973099 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0703. Min Act: -0.0003

Data Index: 839111 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0655. Min Act: -0.0003

Data Index: 426880 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0730. Min Act: -0.0003

Data Index: 1078032 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0663. Min Act: -0.0003

Data Index: 892995 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0676. Min Act: -0.0003

Data Index: 395406 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1257893 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0700. Min Act: -0.0003

Data Index: 856100 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0668. Min Act: -0.0003

Data Index: 673494 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0648. Min Act: -0.0003

Data Index: 384664 (C4 (Web Text))

Max Activating Token Index: 614