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

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

Neuron 4425 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0998. Min Act: -0.0002

Data Index: 1035161 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0887. Min Act: -0.0002

Data Index: 380567 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0988. Min Act: -0.0002

Data Index: 560578 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.1011. Min Act: -0.0002

Data Index: 1128846 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0937. Min Act: -0.0002

Data Index: 802326 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1349029 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0964. Min Act: -0.0002

Data Index: 969732 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0942. Min Act: -0.0002

Data Index: 279126 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0916. Min Act: -0.0002

Data Index: 990831 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0882. Min Act: -0.0002

Data Index: 1027887 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0874. Min Act: -0.0002

Data Index: 48949 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0766. Min Act: -0.0002

Data Index: 947738 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0782. Min Act: -0.0002

Data Index: 577712 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1282487 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0758. Min Act: -0.0002

Data Index: 508544 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0827. Min Act: -0.0002

Data Index: 207450 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0727. Min Act: -0.0002

Data Index: 126071 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0776. Min Act: -0.0002

Data Index: 666160 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0795. Min Act: -0.0002

Data Index: 733667 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0737. Min Act: -0.0002

Data Index: 588078 (C4 (Web Text))

Max Activating Token Index: 999