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

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

Neuron 1172 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1146. Min Act: -0.0005

Data Index: 562406 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1116. Min Act: -0.0005

Data Index: 625061 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1083. Min Act: -0.0005

Data Index: 1340890 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0918. Min Act: -0.0005

Data Index: 1345475 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0908. Min Act: -0.0005

Data Index: 1127580 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0793. Min Act: -0.0005

Data Index: 921288 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0884. Min Act: -0.0005

Data Index: 847899 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0900. Min Act: -0.0005

Data Index: 271487 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0847. Min Act: -0.0005

Data Index: 958698 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0816. Min Act: -0.0005

Data Index: 1000664 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0828. Min Act: -0.0005

Data Index: 1034422 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0856. Min Act: -0.0005

Data Index: 462135 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0814. Min Act: -0.0005

Data Index: 404047 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0815. Min Act: -0.0005

Data Index: 68114 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0794. Min Act: -0.0005

Data Index: 163550 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0684. Min Act: -0.0005

Data Index: 1130945 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0805. Min Act: -0.0005

Data Index: 178885 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0788. Min Act: -0.0005

Data Index: 737334 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0779. Min Act: -0.0004

Data Index: 1355793 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0753. Min Act: -0.0005

Data Index: 1502652 (Python Code)

Max Activating Token Index: 469