Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 714 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0949. Min Act: -0.0002

Data Index: 510912 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0749. Min Act: -0.0002

Data Index: 770010 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1052992 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1171323 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1118213 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0702. Min Act: -0.0002

Data Index: 61911 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0685. Min Act: -0.0002

Data Index: 1132909 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0705. Min Act: -0.0002

Data Index: 866313 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0694. Min Act: -0.0002

Data Index: 884993 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0669. Min Act: -0.0002

Data Index: 703096 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1138962 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0675. Min Act: -0.0002

Data Index: 194237 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1261835 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0670. Min Act: -0.0002

Data Index: 454142 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0671. Min Act: -0.0002

Data Index: 779553 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1084653 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0651. Min Act: -0.0002

Data Index: 569001 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0644. Min Act: -0.0002

Data Index: 218467 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1227900 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0639. Min Act: -0.0002

Data Index: 294931 (C4 (Web Text))

Max Activating Token Index: 335