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

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

Neuron 4506 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: 0.5792. Min Range: -0.5792

Max Act: 0.5792. Min Act: -0.0002

Data Index: 977181 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.5322. Min Act: -0.0002

Data Index: 115285 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.5586. Min Act: -0.0002

Data Index: 837954 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.5483. Min Act: -0.0002

Data Index: 1162065 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.5433. Min Act: -0.0002

Data Index: 545142 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.5215. Min Act: -0.0002

Data Index: 1275656 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.5167. Min Act: -0.0002

Data Index: 1293816 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.5272. Min Act: -0.0002

Data Index: 700881 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.5092. Min Act: -0.0003

Data Index: 237968 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4741. Min Act: -0.0002

Data Index: 641337 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4561. Min Act: -0.0002

Data Index: 1045058 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4865. Min Act: -0.0002

Data Index: 357047 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4735. Min Act: -0.0002

Data Index: 1197608 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4595. Min Act: -0.0002

Data Index: 917110 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4608. Min Act: -0.0002

Data Index: 808520 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4882. Min Act: -0.0002

Data Index: 419483 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4506. Min Act: -0.0002

Data Index: 1163454 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4640. Min Act: -0.0002

Data Index: 96312 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4477. Min Act: -0.0003

Data Index: 388434 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 0.5792. Min Range: -0.5792

Max Act: 0.4556. Min Act: -0.0002

Data Index: 848264 (C4 (Web Text))

Max Activating Token Index: 86