Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 221 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0744. Min Act: -0.0006

Data Index: 841206 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0705. Min Act: -0.0006

Data Index: 919466 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0701. Min Act: -0.0006

Data Index: 154982 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0698. Min Act: -0.0006

Data Index: 370627 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0703. Min Act: -0.0006

Data Index: 963402 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0672. Min Act: -0.0006

Data Index: 1341112 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0717. Min Act: -0.0006

Data Index: 276884 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0653. Min Act: -0.0006

Data Index: 1023335 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0636. Min Act: -0.0006

Data Index: 674140 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0658. Min Act: -0.0006

Data Index: 229474 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0643. Min Act: -0.0006

Data Index: 1157277 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0630. Min Act: -0.0006

Data Index: 697569 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0648. Min Act: -0.0006

Data Index: 390658 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0598. Min Act: -0.0006

Data Index: 1128570 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0635. Min Act: -0.0006

Data Index: 131249 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0632. Min Act: -0.0006

Data Index: 1104944 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0630. Min Act: -0.0006

Data Index: 1126760 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0629. Min Act: -0.0006

Data Index: 566956 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0642. Min Act: -0.0006

Data Index: 992691 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0614. Min Act: -0.0006

Data Index: 1060201 (C4 (Web Text))

Max Activating Token Index: 950