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

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

Neuron 2436 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: 0.0861. Min Range: -0.0861

Max Act: 0.0836. Min Act: -0.0001

Data Index: 444346 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0861. Min Act: -0.0001

Data Index: 57432 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0827. Min Act: -0.0001

Data Index: 588911 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0777. Min Act: -0.0001

Data Index: 455476 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0789. Min Act: -0.0001

Data Index: 282642 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0735. Min Act: -0.0002

Data Index: 164785 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0753. Min Act: -0.0001

Data Index: 85879 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0762. Min Act: -0.0001

Data Index: 671969 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1205363 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0751. Min Act: -0.0001

Data Index: 293059 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0748. Min Act: -0.0001

Data Index: 331635 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0771. Min Act: -0.0001

Data Index: 927806 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0696. Min Act: -0.0001

Data Index: 132443 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0744. Min Act: -0.0001

Data Index: 168882 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0740. Min Act: -0.0001

Data Index: 788310 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0736. Min Act: -0.0001

Data Index: 278026 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0722. Min Act: -0.0002

Data Index: 274743 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0745. Min Act: -0.0001

Data Index: 999414 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0667. Min Act: -0.0001

Data Index: 190462 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0740. Min Act: -0.0001

Data Index: 773884 (C4 (Web Text))

Max Activating Token Index: 648