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

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

Neuron 3617 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1240. Min Act: -0.0002

Data Index: 1114890 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1119. Min Act: -0.0002

Data Index: 775958 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0976. Min Act: -0.0002

Data Index: 1240850 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0984. Min Act: -0.0002

Data Index: 991650 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0973. Min Act: -0.0002

Data Index: 1205190 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0891. Min Act: -0.0002

Data Index: 824851 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0901. Min Act: -0.0002

Data Index: 1200157 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0854. Min Act: -0.0002

Data Index: 901051 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0824. Min Act: -0.0002

Data Index: 141328 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0827. Min Act: -0.0002

Data Index: 567954 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0795. Min Act: -0.0002

Data Index: 856227 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0790. Min Act: -0.0002

Data Index: 1334057 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1062666 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0732. Min Act: -0.0002

Data Index: 1136930 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1272869 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1208572 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0825. Min Act: -0.0002

Data Index: 150893 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0709. Min Act: -0.0002

Data Index: 112919 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0672. Min Act: -0.0002

Data Index: 803366 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1168712 (C4 (Web Text))

Max Activating Token Index: 477