Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4745 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0063. Min Act: -0.0002

Data Index: 246149 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0060. Min Act: -0.0002

Data Index: 847683 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0059. Min Act: -0.0002

Data Index: 778541 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0056. Min Act: -0.0002

Data Index: 985122 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0055. Min Act: -0.0002

Data Index: 389227 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0054. Min Act: -0.0002

Data Index: 252429 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0050. Min Act: -0.0002

Data Index: 869123 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1041889 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0050. Min Act: -0.0002

Data Index: 658499 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1288403 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0049. Min Act: -0.0002

Data Index: 1175785 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0047. Min Act: -0.0002

Data Index: 874057 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0047. Min Act: -0.0002

Data Index: 1083115 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0046. Min Act: -0.0002

Data Index: 723662 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0045. Min Act: -0.0002

Data Index: 1326033 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0046. Min Act: -0.0002

Data Index: 498132 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0045. Min Act: -0.0002

Data Index: 1086238 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0044. Min Act: -0.0002

Data Index: 1302470 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0044. Min Act: -0.0002

Data Index: 1166171 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0044. Min Act: -0.0002

Data Index: 467879 (C4 (Web Text))

Max Activating Token Index: 793