Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 315 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1155443 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1131923 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1076567 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0590. Min Act: -0.0002

Data Index: 118116 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0585. Min Act: -0.0002

Data Index: 85386 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0555. Min Act: -0.0002

Data Index: 641567 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0526. Min Act: -0.0002

Data Index: 108385 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1034656 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0535. Min Act: -0.0002

Data Index: 85316 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0539. Min Act: -0.0002

Data Index: 175068 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0560. Min Act: -0.0002

Data Index: 461019 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0495. Min Act: -0.0002

Data Index: 289862 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0543. Min Act: -0.0002

Data Index: 292395 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1098364 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0524. Min Act: -0.0002

Data Index: 310126 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0554. Min Act: -0.0002

Data Index: 1346192 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0512. Min Act: -0.0002

Data Index: 150844 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0511. Min Act: -0.0002

Data Index: 569806 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0492. Min Act: -0.0002

Data Index: 257570 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1217103 (C4 (Web Text))

Max Activating Token Index: 225