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

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

Neuron 582 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1383. Min Act: -0.0005

Data Index: 36130 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1130. Min Act: -0.0005

Data Index: 16224 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1116. Min Act: -0.0005

Data Index: 153709 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1056. Min Act: -0.0005

Data Index: 235291 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0990. Min Act: -0.0005

Data Index: 342766 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0953. Min Act: -0.0005

Data Index: 493759 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0912. Min Act: -0.0005

Data Index: 1244801 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0899. Min Act: -0.0005

Data Index: 667093 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0898. Min Act: -0.0005

Data Index: 764578 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0916. Min Act: -0.0005

Data Index: 650981 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0902. Min Act: -0.0005

Data Index: 1344393 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0909. Min Act: -0.0005

Data Index: 796582 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0920. Min Act: -0.0005

Data Index: 451996 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0904. Min Act: -0.0005

Data Index: 283771 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0926. Min Act: -0.0005

Data Index: 1007156 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0893. Min Act: -0.0005

Data Index: 1173023 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0897. Min Act: -0.0005

Data Index: 779820 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0865. Min Act: -0.0005

Data Index: 1232029 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0882. Min Act: -0.0005

Data Index: 106050 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0844. Min Act: -0.0005

Data Index: 1101422 (C4 (Web Text))

Max Activating Token Index: 184