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

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

Neuron 239 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: 0.0098. Min Range: -0.0098

Max Act: 0.0096. Min Act: -0.0006

Data Index: 825474 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0098. Min Act: -0.0006

Data Index: 849660 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0097. Min Act: -0.0006

Data Index: 394739 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0095. Min Act: -0.0006

Data Index: 269149 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0093. Min Act: -0.0006

Data Index: 23605 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0096. Min Act: -0.0006

Data Index: 962242 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0094. Min Act: -0.0006

Data Index: 431107 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0094. Min Act: -0.0006

Data Index: 1322878 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1060002 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0095. Min Act: -0.0006

Data Index: 387048 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0092. Min Act: -0.0006

Data Index: 873767 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0095. Min Act: -0.0006

Data Index: 964557 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0094. Min Act: -0.0006

Data Index: 807150 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1093560 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0088. Min Act: -0.0006

Data Index: 718554 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1132398 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0092. Min Act: -0.0006

Data Index: 561821 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0092. Min Act: -0.0006

Data Index: 270510 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0092. Min Act: -0.0006

Data Index: 949601 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0092. Min Act: -0.0006

Data Index: 646159 (C4 (Web Text))

Max Activating Token Index: 649