Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3252 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0025. Min Act: -0.0002

Data Index: 305333 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0025. Min Act: -0.0002

Data Index: 905828 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0025. Min Act: -0.0002

Data Index: 928517 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0024. Min Act: -0.0002

Data Index: 863067 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0024. Min Act: -0.0002

Data Index: 499885 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0024. Min Act: -0.0002

Data Index: 2503 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0024. Min Act: -0.0002

Data Index: 379856 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0024. Min Act: -0.0002

Data Index: 1448310 (Python Code)

Max Activating Token Index: 116

Text #8

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0024. Min Act: -0.0002

Data Index: 956733 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0024. Min Act: -0.0002

Data Index: 551609 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0023. Min Act: -0.0002

Data Index: 354148 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0024. Min Act: -0.0002

Data Index: 119307 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0023. Min Act: -0.0002

Data Index: 821703 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0023. Min Act: -0.0002

Data Index: 968536 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0023. Min Act: -0.0002

Data Index: 424207 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0023. Min Act: -0.0002

Data Index: 172266 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0023. Min Act: -0.0002

Data Index: 128815 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0023. Min Act: -0.0002

Data Index: 593530 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0023. Min Act: -0.0002

Data Index: 1579071 (Python Code)

Max Activating Token Index: 195

Text #19

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0023. Min Act: -0.0002

Data Index: 89606 (C4 (Web Text))

Max Activating Token Index: 221