Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 275 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0915. Min Act: -0.0001

Data Index: 116223 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0874. Min Act: -0.0002

Data Index: 769789 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0850. Min Act: -0.0002

Data Index: 618046 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0823. Min Act: -0.0001

Data Index: 234325 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0774. Min Act: -0.0001

Data Index: 781272 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0759. Min Act: -0.0001

Data Index: 1107472 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0772. Min Act: -0.0001

Data Index: 283980 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0743. Min Act: -0.0001

Data Index: 466415 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0767. Min Act: -0.0001

Data Index: 574265 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0771. Min Act: -0.0002

Data Index: 419384 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0753. Min Act: -0.0001

Data Index: 486445 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0752. Min Act: -0.0001

Data Index: 681178 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0751. Min Act: -0.0001

Data Index: 330010 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0729. Min Act: -0.0001

Data Index: 922561 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0738. Min Act: -0.0002

Data Index: 198134 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0720. Min Act: -0.0001

Data Index: 167894 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1243795 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1149172 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0740. Min Act: -0.0001

Data Index: 796187 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0765. Min Act: -0.0001

Data Index: 1082798 (C4 (Web Text))

Max Activating Token Index: 64