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

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

Neuron 428 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: 0.0955. Min Range: -0.0955

Max Act: 0.0955. Min Act: -0.0002

Data Index: 1226996 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0923. Min Act: -0.0002

Data Index: 1203217 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1309115 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0822. Min Act: -0.0002

Data Index: 546128 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0788. Min Act: -0.0002

Data Index: 286132 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1072585 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0766. Min Act: -0.0002

Data Index: 745296 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1193518 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0609. Min Act: -0.0002

Data Index: 902271 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0575. Min Act: -0.0002

Data Index: 36877 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0606. Min Act: -0.0002

Data Index: 47440 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0580. Min Act: -0.0002

Data Index: 155657 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0596. Min Act: -0.0002

Data Index: 195287 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0569. Min Act: -0.0002

Data Index: 312841 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1165086 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0546. Min Act: -0.0002

Data Index: 742435 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0574. Min Act: -0.0002

Data Index: 496384 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0549. Min Act: -0.0002

Data Index: 816613 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0519. Min Act: -0.0002

Data Index: 411893 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1067308 (C4 (Web Text))

Max Activating Token Index: 685