Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1795 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.1075. Min Act: -0.0000

Data Index: 1369972 (Python Code)

Max Activating Token Index: 335

Text #1

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0881. Min Act: -0.0000

Data Index: 124014 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0785. Min Act: -0.0000

Data Index: 818353 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0866. Min Act: -0.0000

Data Index: 367919 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0747. Min Act: -0.0000

Data Index: 1212660 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0831. Min Act: -0.0000

Data Index: 734130 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0775. Min Act: -0.0000

Data Index: 253032 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0766. Min Act: -0.0000

Data Index: 1338905 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0786. Min Act: -0.0000

Data Index: 512921 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0730. Min Act: -0.0000

Data Index: 206760 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0760. Min Act: -0.0000

Data Index: 666127 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0781. Min Act: -0.0000

Data Index: 1204535 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0693. Min Act: -0.0000

Data Index: 276075 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0807. Min Act: -0.0000

Data Index: 390861 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0650. Min Act: -0.0000

Data Index: 609184 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0706. Min Act: -0.0000

Data Index: 246487 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0647. Min Act: -0.0000

Data Index: 925676 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0693. Min Act: -0.0000

Data Index: 863057 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0714. Min Act: -0.0000

Data Index: 889575 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0631. Min Act: -0.0000

Data Index: 295156 (C4 (Web Text))

Max Activating Token Index: 106