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

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

Neuron 5 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: 0.0959. Min Range: -0.0959

Max Act: 0.0959. Min Act: -0.0002

Data Index: 530203 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1143353 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0832. Min Act: -0.0002

Data Index: 345691 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1329862 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1177839 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1021170 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0696. Min Act: -0.0002

Data Index: 183959 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0740. Min Act: -0.0002

Data Index: 688318 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0753. Min Act: -0.0002

Data Index: 848713 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1064674 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1081094 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1141059 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0731. Min Act: -0.0002

Data Index: 915015 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0738. Min Act: -0.0002

Data Index: 362488 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0723. Min Act: -0.0002

Data Index: 611591 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0699. Min Act: -0.0002

Data Index: 605110 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0714. Min Act: -0.0001

Data Index: 406253 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1317664 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0690. Min Act: -0.0002

Data Index: 1212553 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0721. Min Act: -0.0002

Data Index: 1048794 (C4 (Web Text))

Max Activating Token Index: 597