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

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

Neuron 3790 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: 0.0975. Min Range: -0.0975

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1023901 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1323640 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0900. Min Act: -0.0001

Data Index: 3142 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0774. Min Act: -0.0001

Data Index: 286903 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0756. Min Act: -0.0001

Data Index: 696536 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0735. Min Act: -0.0001

Data Index: 753642 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0698. Min Act: -0.0001

Data Index: 707914 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0709. Min Act: -0.0000

Data Index: 194364 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0729. Min Act: -0.0000

Data Index: 1147734 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0693. Min Act: -0.0001

Data Index: 404975 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0685. Min Act: -0.0000

Data Index: 775736 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0713. Min Act: -0.0001

Data Index: 928820 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0668. Min Act: -0.0001

Data Index: 1096619 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0641. Min Act: -0.0000

Data Index: 963637 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1072340 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0668. Min Act: -0.0001

Data Index: 36046 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0687. Min Act: -0.0001

Data Index: 406683 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0639. Min Act: -0.0001

Data Index: 166950 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0658. Min Act: -0.0001

Data Index: 627417 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0657. Min Act: -0.0001

Data Index: 1043400 (C4 (Web Text))

Max Activating Token Index: 984