Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3450 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0023. Min Act: -0.0003

Data Index: 1094267 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0022. Min Act: -0.0003

Data Index: 1141861 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0021. Min Act: -0.0003

Data Index: 1172717 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0022. Min Act: -0.0003

Data Index: 102698 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0019. Min Act: -0.0003

Data Index: 905740 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0020. Min Act: -0.0003

Data Index: 1017869 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0018. Min Act: -0.0003

Data Index: 627478 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0020. Min Act: -0.0002

Data Index: 1298756 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0017. Min Act: -0.0003

Data Index: 838842 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0017. Min Act: -0.0003

Data Index: 926000 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0017. Min Act: -0.0003

Data Index: 1022385 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0018. Min Act: -0.0003

Data Index: 418127 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0017. Min Act: -0.0003

Data Index: 1168107 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0016. Min Act: -0.0003

Data Index: 524512 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0017. Min Act: -0.0003

Data Index: 591747 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0018. Min Act: -0.0003

Data Index: 421467 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0018. Min Act: -0.0003

Data Index: 1150261 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0016. Min Act: -0.0003

Data Index: 115619 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0017. Min Act: -0.0003

Data Index: 1044492 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.0023. Min Range: -0.0023

Max Act: 0.0017. Min Act: -0.0003

Data Index: 419192 (C4 (Web Text))

Max Activating Token Index: 245