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

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

Neuron 4619 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.1071. Min Act: -0.0000

Data Index: 209700 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0984. Min Act: -0.0000

Data Index: 586687 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0952. Min Act: -0.0000

Data Index: 724271 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0937. Min Act: -0.0000

Data Index: 710611 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0914. Min Act: -0.0000

Data Index: 479372 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0845. Min Act: -0.0000

Data Index: 1134461 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0843. Min Act: -0.0000

Data Index: 323358 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0877. Min Act: -0.0000

Data Index: 866189 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0862. Min Act: -0.0000

Data Index: 295380 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0887. Min Act: -0.0000

Data Index: 304187 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0857. Min Act: -0.0000

Data Index: 160772 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0783. Min Act: -0.0000

Data Index: 1165768 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0830. Min Act: -0.0000

Data Index: 155631 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0707. Min Act: -0.0000

Data Index: 291923 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0764. Min Act: -0.0000

Data Index: 867275 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0754. Min Act: -0.0000

Data Index: 1292754 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0781. Min Act: -0.0000

Data Index: 1314909 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0776. Min Act: -0.0000

Data Index: 141933 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0768. Min Act: -0.0000

Data Index: 664762 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0769. Min Act: -0.0000

Data Index: 528243 (C4 (Web Text))

Max Activating Token Index: 250