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

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

Neuron 1764 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1321927 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0098. Min Act: -0.0006

Data Index: 747796 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1281120 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0095. Min Act: -0.0006

Data Index: 364008 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0094. Min Act: -0.0006

Data Index: 1175442 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0094. Min Act: -0.0006

Data Index: 317153 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0093. Min Act: -0.0005

Data Index: 549903 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0093. Min Act: -0.0005

Data Index: 1231880 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0092. Min Act: -0.0005

Data Index: 593813 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0094. Min Act: -0.0006

Data Index: 167215 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0089. Min Act: -0.0006

Data Index: 262401 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0089. Min Act: -0.0006

Data Index: 1269771 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0091. Min Act: -0.0006

Data Index: 295621 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0091. Min Act: -0.0006

Data Index: 485501 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1006845 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0090. Min Act: -0.0005

Data Index: 1099738 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0086. Min Act: -0.0006

Data Index: 369759 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0086. Min Act: -0.0006

Data Index: 422782 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0088. Min Act: -0.0006

Data Index: 970969 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1059801 (C4 (Web Text))

Max Activating Token Index: 87