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

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

Neuron 392 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0913. Min Act: -0.0002

Data Index: 1218191 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0865. Min Act: -0.0002

Data Index: 969526 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0774. Min Act: -0.0002

Data Index: 159069 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1011943 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0794. Min Act: -0.0002

Data Index: 226057 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1315845 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0739. Min Act: -0.0002

Data Index: 176558 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0688. Min Act: -0.0001

Data Index: 1134181 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0709. Min Act: -0.0002

Data Index: 23577 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0677. Min Act: -0.0002

Data Index: 408558 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1190567 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0669. Min Act: -0.0002

Data Index: 136145 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0688. Min Act: -0.0002

Data Index: 248116 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0688. Min Act: -0.0002

Data Index: 38684 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0685. Min Act: -0.0002

Data Index: 435673 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0704. Min Act: -0.0002

Data Index: 953568 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0672. Min Act: -0.0002

Data Index: 680264 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1079368 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1308038 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0663. Min Act: -0.0002

Data Index: 881449 (C4 (Web Text))

Max Activating Token Index: 830