Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1000 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1255. Min Act: -0.0002

Data Index: 473868 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1035. Min Act: -0.0002

Data Index: 544724 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1006. Min Act: -0.0002

Data Index: 501746 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0936. Min Act: -0.0002

Data Index: 625396 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0866. Min Act: -0.0002

Data Index: 265674 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0889. Min Act: -0.0002

Data Index: 444969 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0882. Min Act: -0.0002

Data Index: 532268 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0876. Min Act: -0.0002

Data Index: 144408 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0898. Min Act: -0.0002

Data Index: 30518 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0862. Min Act: -0.0002

Data Index: 900656 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1048324 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0857. Min Act: -0.0002

Data Index: 194345 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0830. Min Act: -0.0002

Data Index: 520779 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1143838 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0824. Min Act: -0.0002

Data Index: 301912 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0814. Min Act: -0.0002

Data Index: 633148 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0814. Min Act: -0.0002

Data Index: 773838 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0771. Min Act: -0.0002

Data Index: 680556 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0803. Min Act: -0.0002

Data Index: 42731 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0763. Min Act: -0.0002

Data Index: 430141 (C4 (Web Text))

Max Activating Token Index: 635