Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1069 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1291. Min Act: -0.0000

Data Index: 1309638 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0905. Min Act: -0.0000

Data Index: 1132662 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0954. Min Act: -0.0000

Data Index: 710412 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0959. Min Act: -0.0000

Data Index: 499784 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0862. Min Act: -0.0000

Data Index: 641837 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0855. Min Act: -0.0000

Data Index: 540059 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0861. Min Act: -0.0000

Data Index: 575685 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0868. Min Act: -0.0000

Data Index: 1037975 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0796. Min Act: -0.0000

Data Index: 799935 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0846. Min Act: -0.0000

Data Index: 84907 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0863. Min Act: -0.0000

Data Index: 139200 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0751. Min Act: -0.0000

Data Index: 332349 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0797. Min Act: -0.0000

Data Index: 453478 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0785. Min Act: -0.0000

Data Index: 1286746 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0782. Min Act: -0.0000

Data Index: 475666 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0723. Min Act: -0.0000

Data Index: 873010 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0749. Min Act: -0.0000

Data Index: 661598 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0910. Min Act: -0.0000

Data Index: 1176248 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0732. Min Act: -0.0000

Data Index: 1057244 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1129860 (C4 (Web Text))

Max Activating Token Index: 330