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

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

Neuron 50 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0094. Min Act: -0.0006

Data Index: 1242437 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0097. Min Act: -0.0006

Data Index: 16413 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0086. Min Act: -0.0006

Data Index: 988322 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0087. Min Act: -0.0006

Data Index: 1064054 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0074. Min Act: -0.0006

Data Index: 855876 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0078. Min Act: -0.0006

Data Index: 604642 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0074. Min Act: -0.0006

Data Index: 175268 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0078. Min Act: -0.0006

Data Index: 249035 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0080. Min Act: -0.0006

Data Index: 1252726 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0077. Min Act: -0.0006

Data Index: 1051602 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0073. Min Act: -0.0006

Data Index: 304993 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0073. Min Act: -0.0006

Data Index: 448510 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0072. Min Act: -0.0006

Data Index: 1287049 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0074. Min Act: -0.0006

Data Index: 668820 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0071. Min Act: -0.0006

Data Index: 79912 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0077. Min Act: -0.0006

Data Index: 125308 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0077. Min Act: -0.0006

Data Index: 1123537 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0073. Min Act: -0.0006

Data Index: 851854 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0076. Min Act: -0.0006

Data Index: 782271 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0070. Min Act: -0.0006

Data Index: 191712 (C4 (Web Text))

Max Activating Token Index: 452