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

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

Neuron 4041 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0763. Min Act: -0.0003

Data Index: 858628 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0758. Min Act: -0.0002

Data Index: 13304 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0748. Min Act: -0.0002

Data Index: 510890 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1217074 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0726. Min Act: -0.0003

Data Index: 1175571 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0692. Min Act: -0.0003

Data Index: 591604 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0708. Min Act: -0.0002

Data Index: 669640 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0670. Min Act: -0.0003

Data Index: 1301510 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0677. Min Act: -0.0002

Data Index: 701252 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0688. Min Act: -0.0003

Data Index: 678114 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0676. Min Act: -0.0003

Data Index: 58581 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0685. Min Act: -0.0002

Data Index: 73052 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0670. Min Act: -0.0003

Data Index: 613710 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0656. Min Act: -0.0002

Data Index: 972009 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0634. Min Act: -0.0002

Data Index: 476929 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1161415 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0631. Min Act: -0.0003

Data Index: 356674 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1013765 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0626. Min Act: -0.0002

Data Index: 187164 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0617. Min Act: -0.0003

Data Index: 84074 (C4 (Web Text))

Max Activating Token Index: 255