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

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

Neuron 3764 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: 5.3876. Min Range: -5.3876

Max Act: 5.3876. Min Act: -0.0000

Data Index: 153732 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 5.3876. Min Range: -5.3876

Max Act: 4.5808. Min Act: -0.0000

Data Index: 612281 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 5.3876. Min Range: -5.3876

Max Act: 4.8915. Min Act: -0.0000

Data Index: 809437 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 5.3876. Min Range: -5.3876

Max Act: 4.6553. Min Act: -0.0000

Data Index: 206467 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 5.3876. Min Range: -5.3876

Max Act: 4.8023. Min Act: -0.0000

Data Index: 1019172 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 5.3876. Min Range: -5.3876

Max Act: 4.7682. Min Act: -0.0000

Data Index: 781374 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 5.3876. Min Range: -5.3876

Max Act: 4.7759. Min Act: -0.0000

Data Index: 179819 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 5.3876. Min Range: -5.3876

Max Act: 4.7631. Min Act: -0.0000

Data Index: 666977 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 5.3876. Min Range: -5.3876

Max Act: 4.7286. Min Act: -0.0000

Data Index: 34040 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 5.3876. Min Range: -5.3876

Max Act: 4.4947. Min Act: -0.0000

Data Index: 1253524 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 5.3876. Min Range: -5.3876

Max Act: 4.4194. Min Act: -0.0000

Data Index: 1249081 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 5.3876. Min Range: -5.3876

Max Act: 4.8210. Min Act: -0.0000

Data Index: 942068 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 5.3876. Min Range: -5.3876

Max Act: 4.6241. Min Act: -0.0000

Data Index: 818672 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 5.3876. Min Range: -5.3876

Max Act: 4.7647. Min Act: 0.0000

Data Index: 7723 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 5.3876. Min Range: -5.3876

Max Act: 4.6728. Min Act: -0.0000

Data Index: 898156 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 5.3876. Min Range: -5.3876

Max Act: 4.6185. Min Act: -0.0000

Data Index: 370020 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 5.3876. Min Range: -5.3876

Max Act: 4.2859. Min Act: -0.0000

Data Index: 711845 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 5.3876. Min Range: -5.3876

Max Act: 4.7180. Min Act: -0.0000

Data Index: 652150 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 5.3876. Min Range: -5.3876

Max Act: 4.3637. Min Act: -0.0000

Data Index: 26903 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 5.3876. Min Range: -5.3876

Max Act: 4.5062. Min Act: -0.0000

Data Index: 201273 (C4 (Web Text))

Max Activating Token Index: 159