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

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

Neuron 4052 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.9558. Min Act: -0.0000

Data Index: 809603 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.7271. Min Act: -0.0000

Data Index: 1098750 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.5982. Min Act: -0.0000

Data Index: 1093612 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.5884. Min Act: -0.0000

Data Index: 39102 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.4528. Min Act: -0.0000

Data Index: 1057122 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.5142. Min Act: -0.0000

Data Index: 1146306 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.5897. Min Act: -0.0000

Data Index: 484818 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.3931. Min Act: -0.0000

Data Index: 1012856 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.3617. Min Act: -0.0000

Data Index: 310755 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.4456. Min Act: -0.0000

Data Index: 630425 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.4856. Min Act: -0.0000

Data Index: 93956 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.3902. Min Act: -0.0000

Data Index: 198360 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.3844. Min Act: -0.0000

Data Index: 83703 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.3836. Min Act: -0.0000

Data Index: 509196 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.3806. Min Act: -0.0000

Data Index: 69544 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.3307. Min Act: -0.0000

Data Index: 612575 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.3309. Min Act: -0.0000

Data Index: 154005 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.2434. Min Act: -0.0000

Data Index: 1347107 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.2747. Min Act: -0.0000

Data Index: 368154 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 1.9558. Min Range: -1.9558

Max Act: 1.1790. Min Act: 0.0001

Data Index: 11220 (C4 (Web Text))

Max Activating Token Index: 287