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

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

Neuron 40 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: 0.0889. Min Range: -0.0889

Max Act: 0.0803. Min Act: -0.0003

Data Index: 226297 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0703. Min Act: -0.0004

Data Index: 24980 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0710. Min Act: -0.0004

Data Index: 124197 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0818. Min Act: -0.0003

Data Index: 787964 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0708. Min Act: -0.0004

Data Index: 590572 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0762. Min Act: -0.0003

Data Index: 639786 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0786. Min Act: -0.0003

Data Index: 694311 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0812. Min Act: -0.0003

Data Index: 995228 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0749. Min Act: -0.0004

Data Index: 353491 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0889. Min Act: -0.0003

Data Index: 1096761 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0767. Min Act: -0.0003

Data Index: 1233086 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0646. Min Act: -0.0003

Data Index: 141289 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0699. Min Act: -0.0003

Data Index: 1231850 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0743. Min Act: -0.0003

Data Index: 346958 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0711. Min Act: -0.0003

Data Index: 823242 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0742. Min Act: -0.0004

Data Index: 1238014 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0586. Min Act: -0.0003

Data Index: 906793 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0646. Min Act: -0.0003

Data Index: 117869 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0752. Min Act: -0.0003

Data Index: 378164 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0727. Min Act: -0.0003

Data Index: 732241 (C4 (Web Text))

Max Activating Token Index: 794