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

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

Neuron 1824 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: 0.1073. Min Range: -0.1073

Max Act: 0.1073. Min Act: -0.0002

Data Index: 690002 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0907. Min Act: -0.0002

Data Index: 555174 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0923. Min Act: -0.0002

Data Index: 184219 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0899. Min Act: -0.0002

Data Index: 949014 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0868. Min Act: -0.0002

Data Index: 1336456 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0838. Min Act: -0.0001

Data Index: 753946 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0830. Min Act: -0.0002

Data Index: 508716 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0805. Min Act: -0.0002

Data Index: 632123 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0843. Min Act: -0.0002

Data Index: 86951 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0824. Min Act: -0.0002

Data Index: 444122 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0854. Min Act: -0.0001

Data Index: 343487 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0839. Min Act: -0.0002

Data Index: 1258427 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0819. Min Act: -0.0002

Data Index: 276460 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1024069 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0766. Min Act: -0.0002

Data Index: 527824 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0826. Min Act: -0.0002

Data Index: 48856 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0810. Min Act: -0.0002

Data Index: 946588 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0820. Min Act: -0.0002

Data Index: 700431 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0821. Min Act: -0.0002

Data Index: 104142 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0821. Min Act: -0.0002

Data Index: 423278 (C4 (Web Text))

Max Activating Token Index: 93