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

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

Neuron 1563 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0113. Min Act: -0.0005

Data Index: 705064 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0104. Min Act: -0.0005

Data Index: 17561 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0105. Min Act: -0.0005

Data Index: 809899 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0096. Min Act: -0.0005

Data Index: 931764 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0088. Min Act: -0.0005

Data Index: 242140 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0090. Min Act: -0.0005

Data Index: 149425 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0089. Min Act: -0.0005

Data Index: 1270707 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0086. Min Act: -0.0005

Data Index: 1265635 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0075. Min Act: -0.0005

Data Index: 587697 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0070. Min Act: -0.0005

Data Index: 424221 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0073. Min Act: -0.0005

Data Index: 557411 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0072. Min Act: -0.0005

Data Index: 1301055 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0071. Min Act: -0.0005

Data Index: 958605 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0072. Min Act: -0.0005

Data Index: 1258906 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0069. Min Act: -0.0005

Data Index: 499869 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0072. Min Act: -0.0005

Data Index: 185034 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1127973 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0071. Min Act: -0.0005

Data Index: 957737 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0071. Min Act: -0.0005

Data Index: 988784 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0074. Min Act: -0.0005

Data Index: 94570 (C4 (Web Text))

Max Activating Token Index: 279