Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1550 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0028. Min Act: -0.0006

Data Index: 1006104 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0028. Min Act: -0.0006

Data Index: 738479 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0026. Min Act: -0.0005

Data Index: 1347312 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0026. Min Act: -0.0005

Data Index: 981711 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0024. Min Act: -0.0006

Data Index: 1085574 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0023. Min Act: -0.0006

Data Index: 2892 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0023. Min Act: -0.0005

Data Index: 880992 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0023. Min Act: -0.0005

Data Index: 72240 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0005

Data Index: 1037305 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0005

Data Index: 468403 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0006

Data Index: 865125 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0006

Data Index: 999427 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0006

Data Index: 1012899 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0005

Data Index: 944929 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0006

Data Index: 835418 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0005

Data Index: 682810 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0021. Min Act: -0.0005

Data Index: 250095 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0021. Min Act: -0.0005

Data Index: 642716 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0021. Min Act: -0.0006

Data Index: 677830 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0021. Min Act: -0.0005

Data Index: 919669 (C4 (Web Text))

Max Activating Token Index: 24