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

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

Neuron 4322 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.6876. Min Act: -0.0001

Data Index: 486191 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.6380. Min Act: -0.0001

Data Index: 519907 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.6276. Min Act: -0.0001

Data Index: 316784 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.6215. Min Act: -0.0001

Data Index: 800890 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.6374. Min Act: -0.0001

Data Index: 499045 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.6029. Min Act: -0.0001

Data Index: 1186067 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5764. Min Act: -0.0001

Data Index: 700130 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5813. Min Act: -0.0001

Data Index: 1173128 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5484. Min Act: -0.0001

Data Index: 742142 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5564. Min Act: -0.0001

Data Index: 453305 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5738. Min Act: -0.0001

Data Index: 315990 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5291. Min Act: -0.0001

Data Index: 658172 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5072. Min Act: -0.0001

Data Index: 833143 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5189. Min Act: -0.0001

Data Index: 731409 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5722. Min Act: -0.0001

Data Index: 681217 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5204. Min Act: -0.0001

Data Index: 672413 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5211. Min Act: -0.0001

Data Index: 948336 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4768. Min Act: -0.0001

Data Index: 611492 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.4961. Min Act: -0.0001

Data Index: 295283 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.6876. Min Range: -0.6876

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1082425 (C4 (Web Text))

Max Activating Token Index: 586