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

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

Neuron 4632 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0939. Min Act: -0.0002

Data Index: 699419 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0845. Min Act: -0.0002

Data Index: 18551 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0842. Min Act: -0.0002

Data Index: 124167 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0821. Min Act: -0.0002

Data Index: 184361 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0852. Min Act: -0.0002

Data Index: 332451 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1297959 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0815. Min Act: -0.0002

Data Index: 374086 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0822. Min Act: -0.0002

Data Index: 864773 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0803. Min Act: -0.0002

Data Index: 704797 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0790. Min Act: -0.0002

Data Index: 407483 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0796. Min Act: -0.0002

Data Index: 182336 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1156725 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0830. Min Act: -0.0002

Data Index: 223416 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0832. Min Act: -0.0002

Data Index: 1066644 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0804. Min Act: -0.0002

Data Index: 619609 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0781. Min Act: -0.0002

Data Index: 317295 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1134736 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0790. Min Act: -0.0002

Data Index: 228479 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0776. Min Act: -0.0002

Data Index: 19062 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0823. Min Act: -0.0002

Data Index: 992578 (C4 (Web Text))

Max Activating Token Index: 448