Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 50 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1355108 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0772. Min Act: -0.0001

Data Index: 114986 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0786. Min Act: -0.0000

Data Index: 53061 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0752. Min Act: -0.0000

Data Index: 668020 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0687. Min Act: -0.0000

Data Index: 367600 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0713. Min Act: 0.0000

Data Index: 1175050 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0711. Min Act: -0.0000

Data Index: 333540 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0683. Min Act: -0.0000

Data Index: 987518 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0721. Min Act: -0.0001

Data Index: 58600 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0673. Min Act: -0.0000

Data Index: 909323 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0648. Min Act: -0.0000

Data Index: 476241 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0712. Min Act: -0.0000

Data Index: 159596 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0692. Min Act: -0.0000

Data Index: 833502 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0685. Min Act: -0.0000

Data Index: 820315 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0660. Min Act: -0.0000

Data Index: 1318859 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0671. Min Act: -0.0000

Data Index: 411386 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0679. Min Act: -0.0001

Data Index: 41029 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0661. Min Act: -0.0000

Data Index: 171462 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0640. Min Act: -0.0000

Data Index: 385072 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0641. Min Act: -0.0001

Data Index: 715700 (C4 (Web Text))

Max Activating Token Index: 176