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

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

Neuron 3033 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.9569. Min Act: -0.0003

Data Index: 195604 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.8304. Min Act: -0.0002

Data Index: 539547 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.7078. Min Act: -0.0003

Data Index: 693218 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.7665. Min Act: -0.0002

Data Index: 479413 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.7334. Min Act: -0.0002

Data Index: 922362 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.7125. Min Act: -0.0003

Data Index: 363800 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.6928. Min Act: -0.0003

Data Index: 376543 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.6846. Min Act: -0.0003

Data Index: 375131 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.7027. Min Act: -0.0002

Data Index: 1328309 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.7437. Min Act: -0.0003

Data Index: 604689 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.7207. Min Act: -0.0002

Data Index: 193623 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.6516. Min Act: -0.0003

Data Index: 413032 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.7301. Min Act: -0.0002

Data Index: 409511 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.6197. Min Act: -0.0003

Data Index: 152098 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.5942. Min Act: -0.0003

Data Index: 1228722 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.6081. Min Act: -0.0003

Data Index: 1221789 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.6850. Min Act: -0.0003

Data Index: 1138881 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.6851. Min Act: -0.0002

Data Index: 865762 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.5919. Min Act: -0.0002

Data Index: 308138 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.6524. Min Act: -0.0003

Data Index: 1289425 (C4 (Web Text))

Max Activating Token Index: 673