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

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

Neuron 45 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0789. Min Act: -0.0002

Data Index: 745288 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1346296 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0745. Min Act: -0.0002

Data Index: 510568 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0757. Min Act: -0.0002

Data Index: 868433 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0759. Min Act: -0.0002

Data Index: 781885 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0712. Min Act: -0.0002

Data Index: 186089 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0740. Min Act: -0.0002

Data Index: 645985 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0729. Min Act: -0.0001

Data Index: 380398 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0723. Min Act: -0.0002

Data Index: 59123 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0703. Min Act: -0.0002

Data Index: 960991 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0682. Min Act: -0.0002

Data Index: 788571 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0644. Min Act: -0.0002

Data Index: 474072 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0626. Min Act: -0.0002

Data Index: 630809 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0664. Min Act: -0.0002

Data Index: 911575 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0629. Min Act: -0.0002

Data Index: 836616 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1204723 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1144810 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0657. Min Act: -0.0002

Data Index: 1252075 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0627. Min Act: -0.0002

Data Index: 1278078 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0615. Min Act: -0.0002

Data Index: 345957 (C4 (Web Text))

Max Activating Token Index: 983