Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 451 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0987. Min Act: -0.0002

Data Index: 857318 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0836. Min Act: -0.0002

Data Index: 45886 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0828. Min Act: -0.0002

Data Index: 512706 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1041875 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0735. Min Act: -0.0002

Data Index: 797186 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0784. Min Act: -0.0002

Data Index: 535995 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0752. Min Act: -0.0002

Data Index: 249760 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0715. Min Act: -0.0002

Data Index: 961441 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0753. Min Act: -0.0002

Data Index: 121687 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0681. Min Act: -0.0002

Data Index: 859710 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0670. Min Act: -0.0002

Data Index: 597138 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0625. Min Act: -0.0002

Data Index: 810298 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0586. Min Act: -0.0002

Data Index: 47265 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1098777 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0569. Min Act: -0.0002

Data Index: 275584 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0628. Min Act: -0.0002

Data Index: 587747 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0639. Min Act: -0.0002

Data Index: 872270 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1091046 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0624. Min Act: -0.0002

Data Index: 658067 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0610. Min Act: -0.0002

Data Index: 740558 (C4 (Web Text))

Max Activating Token Index: 231