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

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

Neuron 155 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.1017. Min Act: -0.0005

Data Index: 432135 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0917. Min Act: -0.0005

Data Index: 1152377 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0867. Min Act: -0.0005

Data Index: 78866 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0925. Min Act: -0.0005

Data Index: 67810 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0938. Min Act: -0.0005

Data Index: 931828 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0877. Min Act: -0.0005

Data Index: 768990 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0872. Min Act: -0.0005

Data Index: 699661 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0893. Min Act: -0.0005

Data Index: 881614 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0899. Min Act: -0.0005

Data Index: 749766 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0841. Min Act: -0.0005

Data Index: 221017 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0851. Min Act: -0.0005

Data Index: 1072213 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0782. Min Act: -0.0005

Data Index: 732638 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0849. Min Act: -0.0005

Data Index: 232288 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0862. Min Act: -0.0005

Data Index: 491933 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0847. Min Act: -0.0005

Data Index: 773448 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0837. Min Act: -0.0005

Data Index: 209911 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0849. Min Act: -0.0005

Data Index: 460138 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0843. Min Act: -0.0005

Data Index: 35713 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0828. Min Act: -0.0005

Data Index: 531123 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0865. Min Act: -0.0005

Data Index: 123940 (C4 (Web Text))

Max Activating Token Index: 1000