Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1572 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1064501 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0086. Min Act: -0.0006

Data Index: 958191 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0086. Min Act: -0.0006

Data Index: 310692 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0081. Min Act: -0.0006

Data Index: 358787 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0006

Data Index: 353624 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0006

Data Index: 90686 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0082. Min Act: -0.0006

Data Index: 143892 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0079. Min Act: -0.0006

Data Index: 1150843 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0076. Min Act: -0.0006

Data Index: 899904 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0075. Min Act: -0.0006

Data Index: 1338083 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0075. Min Act: -0.0006

Data Index: 444754 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0077. Min Act: -0.0006

Data Index: 203738 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0074. Min Act: -0.0006

Data Index: 421806 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0075. Min Act: -0.0006

Data Index: 390873 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0073. Min Act: -0.0006

Data Index: 478496 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0074. Min Act: -0.0006

Data Index: 356990 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0074. Min Act: -0.0006

Data Index: 57707 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0074. Min Act: -0.0006

Data Index: 925217 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0074. Min Act: -0.0006

Data Index: 228881 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0071. Min Act: -0.0006

Data Index: 73138 (C4 (Web Text))

Max Activating Token Index: 541