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

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

Neuron 2201 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: 0.0942. Min Range: -0.0942

Max Act: 0.0942. Min Act: -0.0002

Data Index: 828787 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0852. Min Act: -0.0003

Data Index: 355322 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0850. Min Act: -0.0003

Data Index: 267350 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0824. Min Act: -0.0003

Data Index: 1299910 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0763. Min Act: -0.0003

Data Index: 927901 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0693. Min Act: -0.0003

Data Index: 44537 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0661. Min Act: -0.0003

Data Index: 655046 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0681. Min Act: -0.0003

Data Index: 1102973 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0712. Min Act: -0.0003

Data Index: 583797 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0674. Min Act: -0.0003

Data Index: 490425 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0710. Min Act: -0.0003

Data Index: 1038710 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0683. Min Act: -0.0003

Data Index: 891754 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1131372 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0693. Min Act: -0.0003

Data Index: 1330150 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0680. Min Act: -0.0003

Data Index: 894764 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0681. Min Act: -0.0003

Data Index: 26190 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0688. Min Act: -0.0003

Data Index: 77459 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0670. Min Act: -0.0003

Data Index: 852651 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0641. Min Act: -0.0003

Data Index: 139547 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0620. Min Act: -0.0003

Data Index: 179668 (C4 (Web Text))

Max Activating Token Index: 707