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

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

Neuron 3039 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0623. Min Act: -0.0002

Data Index: 263799 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0569. Min Act: -0.0002

Data Index: 226169 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1105346 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0529. Min Act: -0.0002

Data Index: 328157 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0567. Min Act: -0.0002

Data Index: 469016 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0537. Min Act: -0.0002

Data Index: 804109 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0532. Min Act: -0.0002

Data Index: 726588 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1231847 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1038806 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0526. Min Act: -0.0002

Data Index: 61586 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0546. Min Act: -0.0002

Data Index: 724883 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0502. Min Act: -0.0002

Data Index: 622084 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0561. Min Act: -0.0002

Data Index: 749476 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0495. Min Act: -0.0002

Data Index: 861634 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0512. Min Act: -0.0002

Data Index: 355045 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1182927 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0513. Min Act: -0.0002

Data Index: 628404 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1190210 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0515. Min Act: -0.0002

Data Index: 54881 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1207680 (C4 (Web Text))

Max Activating Token Index: 18