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

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

Neuron 93 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: 0.0688. Min Range: -0.0688

Max Act: 0.0688. Min Act: -0.0004

Data Index: 192819 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0627. Min Act: -0.0003

Data Index: 296366 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0634. Min Act: -0.0003

Data Index: 987082 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0613. Min Act: -0.0002

Data Index: 20274 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0611. Min Act: -0.0002

Data Index: 937309 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0604. Min Act: -0.0003

Data Index: 358368 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0586. Min Act: -0.0004

Data Index: 1082406 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0584. Min Act: -0.0003

Data Index: 1060049 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1258778 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0586. Min Act: -0.0004

Data Index: 184046 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0595. Min Act: -0.0003

Data Index: 73080 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0571. Min Act: -0.0003

Data Index: 298709 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0566. Min Act: -0.0003

Data Index: 52086 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0549. Min Act: -0.0004

Data Index: 154767 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0558. Min Act: -0.0003

Data Index: 1138016 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0554. Min Act: -0.0003

Data Index: 654423 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0574. Min Act: -0.0003

Data Index: 733568 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0553. Min Act: -0.0004

Data Index: 585697 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1180468 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0550. Min Act: -0.0003

Data Index: 254475 (C4 (Web Text))

Max Activating Token Index: 570