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

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

Neuron 3223 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: 0.0907. Min Range: -0.0907

Max Act: 0.0907. Min Act: -0.0002

Data Index: 99395 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1243393 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0796. Min Act: -0.0002

Data Index: 146589 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0902. Min Act: -0.0002

Data Index: 191580 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0718. Min Act: -0.0002

Data Index: 386670 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0740. Min Act: -0.0002

Data Index: 817826 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0701. Min Act: -0.0002

Data Index: 614442 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0657. Min Act: -0.0002

Data Index: 923436 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0680. Min Act: -0.0002

Data Index: 24656 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0776. Min Act: -0.0002

Data Index: 356688 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1185251 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0761. Min Act: -0.0002

Data Index: 225338 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0653. Min Act: -0.0002

Data Index: 1058944 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0594. Min Act: -0.0002

Data Index: 539474 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0616. Min Act: -0.0002

Data Index: 426719 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0584. Min Act: -0.0002

Data Index: 396090 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0622. Min Act: -0.0002

Data Index: 306473 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0561. Min Act: -0.0002

Data Index: 805017 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0636. Min Act: -0.0002

Data Index: 246718 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0532. Min Act: -0.0002

Data Index: 72487 (C4 (Web Text))

Max Activating Token Index: 824