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

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

Neuron 1474 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0729. Min Act: -0.0003

Data Index: 457212 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0752. Min Act: -0.0003

Data Index: 812596 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0757. Min Act: -0.0003

Data Index: 932657 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0736. Min Act: -0.0003

Data Index: 736134 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0700. Min Act: -0.0003

Data Index: 1091270 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0706. Min Act: -0.0003

Data Index: 1012059 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0717. Min Act: -0.0003

Data Index: 214562 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0685. Min Act: -0.0004

Data Index: 414184 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0700. Min Act: -0.0003

Data Index: 260872 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0706. Min Act: -0.0003

Data Index: 875241 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0707. Min Act: -0.0003

Data Index: 1027747 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0662. Min Act: -0.0003

Data Index: 674180 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0678. Min Act: -0.0003

Data Index: 1119617 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0677. Min Act: -0.0003

Data Index: 621137 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0656. Min Act: -0.0003

Data Index: 546494 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0656. Min Act: -0.0003

Data Index: 36536 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0665. Min Act: -0.0003

Data Index: 446825 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0629. Min Act: -0.0003

Data Index: 135704 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0647. Min Act: -0.0003

Data Index: 1133426 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0655. Min Act: -0.0003

Data Index: 258348 (C4 (Web Text))

Max Activating Token Index: 622