Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1745 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0729. Min Act: -0.0005

Data Index: 1071836 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0732. Min Act: -0.0005

Data Index: 1165495 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0663. Min Act: -0.0005

Data Index: 879513 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0702. Min Act: -0.0005

Data Index: 1345316 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0671. Min Act: -0.0005

Data Index: 1342461 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0685. Min Act: -0.0005

Data Index: 454238 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0669. Min Act: -0.0005

Data Index: 678637 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0680. Min Act: -0.0005

Data Index: 647280 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0672. Min Act: -0.0005

Data Index: 1306310 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0670. Min Act: -0.0005

Data Index: 1526469 (Python Code)

Max Activating Token Index: 547

Text #10

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0691. Min Act: -0.0005

Data Index: 24293 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0658. Min Act: -0.0005

Data Index: 905617 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0685. Min Act: -0.0005

Data Index: 577121 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0660. Min Act: -0.0005

Data Index: 157649 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0671. Min Act: -0.0005

Data Index: 256328 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0646. Min Act: -0.0005

Data Index: 792620 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0632. Min Act: -0.0005

Data Index: 1257810 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0653. Min Act: -0.0005

Data Index: 657151 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0658. Min Act: -0.0005

Data Index: 31686 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0641. Min Act: -0.0005

Data Index: 272184 (C4 (Web Text))

Max Activating Token Index: 936