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

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

Neuron 5140 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.1075. Min Act: -0.0001

Data Index: 517960 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.1013. Min Act: -0.0001

Data Index: 561119 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0938. Min Act: -0.0001

Data Index: 360222 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0993. Min Act: -0.0001

Data Index: 140352 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.1045. Min Act: -0.0001

Data Index: 609078 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0859. Min Act: -0.0001

Data Index: 322533 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0907. Min Act: -0.0001

Data Index: 160254 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0838. Min Act: -0.0001

Data Index: 614904 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0850. Min Act: -0.0001

Data Index: 1320273 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0851. Min Act: -0.0001

Data Index: 178908 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0864. Min Act: -0.0001

Data Index: 861294 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0909. Min Act: -0.0001

Data Index: 322586 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0846. Min Act: -0.0001

Data Index: 490101 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0798. Min Act: -0.0001

Data Index: 988906 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0826. Min Act: -0.0001

Data Index: 70557 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0733. Min Act: -0.0001

Data Index: 60466 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0879. Min Act: -0.0001

Data Index: 72910 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0797. Min Act: -0.0001

Data Index: 971774 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0809. Min Act: -0.0001

Data Index: 811031 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0784. Min Act: -0.0001

Data Index: 754106 (C4 (Web Text))

Max Activating Token Index: 329