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

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

Neuron 2685 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1082. Min Act: -0.0003

Data Index: 1203054 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1067. Min Act: -0.0003

Data Index: 65152 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0923. Min Act: -0.0002

Data Index: 474537 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0911. Min Act: -0.0002

Data Index: 1004062 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0900. Min Act: -0.0003

Data Index: 364485 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0870. Min Act: -0.0003

Data Index: 61053 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0840. Min Act: -0.0003

Data Index: 438707 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0866. Min Act: -0.0003

Data Index: 388503 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0865. Min Act: -0.0003

Data Index: 263460 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1157686 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0848. Min Act: -0.0003

Data Index: 628057 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0845. Min Act: -0.0002

Data Index: 271667 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0841. Min Act: -0.0003

Data Index: 6328 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0809. Min Act: -0.0002

Data Index: 144013 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0827. Min Act: -0.0003

Data Index: 456778 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1189808 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0815. Min Act: -0.0002

Data Index: 88595 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0845. Min Act: -0.0002

Data Index: 1072407 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0782. Min Act: -0.0002

Data Index: 121996 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0816. Min Act: -0.0002

Data Index: 497404 (C4 (Web Text))

Max Activating Token Index: 133