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

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

Neuron 1660 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0871. Min Act: -0.0002

Data Index: 314414 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0792. Min Act: -0.0001

Data Index: 3830 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0851. Min Act: -0.0002

Data Index: 233315 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0884. Min Act: -0.0002

Data Index: 212391 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0757. Min Act: -0.0001

Data Index: 1209555 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0717. Min Act: -0.0001

Data Index: 1210703 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1313822 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0679. Min Act: -0.0002

Data Index: 207828 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0731. Min Act: -0.0001

Data Index: 1188752 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0692. Min Act: -0.0002

Data Index: 616384 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0671. Min Act: -0.0001

Data Index: 1067650 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1226765 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0711. Min Act: -0.0002

Data Index: 558200 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0649. Min Act: -0.0002

Data Index: 305053 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0670. Min Act: -0.0002

Data Index: 200652 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1353806 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0604. Min Act: -0.0002

Data Index: 243330 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0615. Min Act: -0.0002

Data Index: 477359 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0597. Min Act: -0.0001

Data Index: 472190 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1176472 (C4 (Web Text))

Max Activating Token Index: 888