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

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

Neuron 3449 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0922. Min Act: -0.0001

Data Index: 136467 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0911. Min Act: -0.0001

Data Index: 980700 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0897. Min Act: -0.0001

Data Index: 339073 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0791. Min Act: -0.0001

Data Index: 596250 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0727. Min Act: -0.0001

Data Index: 910174 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1007794 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1330458 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0707. Min Act: -0.0001

Data Index: 439993 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0717. Min Act: -0.0000

Data Index: 368413 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0760. Min Act: -0.0001

Data Index: 10419 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0707. Min Act: -0.0001

Data Index: 677706 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0732. Min Act: -0.0001

Data Index: 126556 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0694. Min Act: -0.0001

Data Index: 720270 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0627. Min Act: -0.0001

Data Index: 1316498 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0707. Min Act: -0.0001

Data Index: 230177 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0692. Min Act: -0.0001

Data Index: 1043263 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0649. Min Act: -0.0001

Data Index: 24633 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0641. Min Act: -0.0001

Data Index: 753778 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0665. Min Act: -0.0001

Data Index: 8105 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0517. Min Act: -0.0000

Data Index: 893072 (C4 (Web Text))

Max Activating Token Index: 286