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

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

Neuron 1407 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.1079. Min Act: -0.0002

Data Index: 403306 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.1044. Min Act: -0.0002

Data Index: 816015 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.1063. Min Act: -0.0002

Data Index: 12565 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.1017. Min Act: -0.0002

Data Index: 50664 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0981. Min Act: -0.0002

Data Index: 751967 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0990. Min Act: -0.0002

Data Index: 920162 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0985. Min Act: -0.0002

Data Index: 149822 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0931. Min Act: -0.0002

Data Index: 1236104 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0960. Min Act: -0.0002

Data Index: 39523 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0918. Min Act: -0.0002

Data Index: 247515 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0880. Min Act: -0.0002

Data Index: 91114 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0909. Min Act: -0.0002

Data Index: 842704 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0897. Min Act: -0.0002

Data Index: 649543 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1080625 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0802. Min Act: -0.0002

Data Index: 25951 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0866. Min Act: -0.0002

Data Index: 639289 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0873. Min Act: -0.0002

Data Index: 380398 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0830. Min Act: -0.0002

Data Index: 9011 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0856. Min Act: -0.0002

Data Index: 866414 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1050611 (C4 (Web Text))

Max Activating Token Index: 97