Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3046 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0852. Min Act: -0.0004

Data Index: 93576 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0679. Min Act: -0.0004

Data Index: 133174 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0781. Min Act: -0.0004

Data Index: 649146 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0817. Min Act: -0.0004

Data Index: 1212765 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0848. Min Act: -0.0004

Data Index: 1015906 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0824. Min Act: -0.0004

Data Index: 1305882 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0818. Min Act: -0.0004

Data Index: 981290 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0779. Min Act: -0.0004

Data Index: 827146 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0641. Min Act: -0.0004

Data Index: 1033125 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0699. Min Act: -0.0004

Data Index: 1078332 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0730. Min Act: -0.0004

Data Index: 371793 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0781. Min Act: -0.0004

Data Index: 830606 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0779. Min Act: -0.0004

Data Index: 523859 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0746. Min Act: -0.0004

Data Index: 100800 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0743. Min Act: -0.0004

Data Index: 250667 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0828. Min Act: -0.0004

Data Index: 1206502 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0704. Min Act: -0.0004

Data Index: 489814 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0751. Min Act: -0.0004

Data Index: 79493 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0676. Min Act: -0.0004

Data Index: 1268077 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0642. Min Act: -0.0004

Data Index: 1087644 (C4 (Web Text))

Max Activating Token Index: 575