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

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

Neuron 1874 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: 0.0102. Min Range: -0.0102

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1239268 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0099. Min Act: -0.0005

Data Index: 57636 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0095. Min Act: -0.0005

Data Index: 330158 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0095. Min Act: -0.0005

Data Index: 701127 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0096. Min Act: -0.0005

Data Index: 760858 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0097. Min Act: -0.0005

Data Index: 68947 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0097. Min Act: -0.0005

Data Index: 1153652 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0092. Min Act: -0.0006

Data Index: 1123820 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0099. Min Act: -0.0006

Data Index: 40523 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0093. Min Act: -0.0005

Data Index: 259222 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0094. Min Act: -0.0005

Data Index: 575374 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0095. Min Act: -0.0006

Data Index: 684193 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1283354 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0095. Min Act: -0.0005

Data Index: 1189287 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0090. Min Act: -0.0005

Data Index: 684714 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0092. Min Act: -0.0005

Data Index: 1592242 (Python Code)

Max Activating Token Index: 83

Text #16

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0089. Min Act: -0.0006

Data Index: 778747 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0091. Min Act: -0.0006

Data Index: 478111 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0091. Min Act: -0.0005

Data Index: 1166816 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0089. Min Act: -0.0005

Data Index: 616518 (C4 (Web Text))

Max Activating Token Index: 10