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

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

Neuron 731 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: 0.0892. Min Range: -0.0892

Max Act: 0.0884. Min Act: -0.0004

Data Index: 1057694 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0858. Min Act: -0.0004

Data Index: 1304767 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0892. Min Act: -0.0004

Data Index: 270835 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0821. Min Act: -0.0004

Data Index: 260793 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0825. Min Act: -0.0004

Data Index: 196548 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0819. Min Act: -0.0004

Data Index: 1057326 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0861. Min Act: -0.0004

Data Index: 118886 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0838. Min Act: -0.0004

Data Index: 199778 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0835. Min Act: -0.0004

Data Index: 1311605 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0836. Min Act: -0.0004

Data Index: 517106 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0795. Min Act: -0.0004

Data Index: 726890 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0824. Min Act: -0.0004

Data Index: 661579 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0824. Min Act: -0.0004

Data Index: 951657 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0851. Min Act: -0.0004

Data Index: 910114 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0769. Min Act: -0.0004

Data Index: 188705 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0798. Min Act: -0.0004

Data Index: 588325 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0764. Min Act: -0.0004

Data Index: 328757 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0821. Min Act: -0.0004

Data Index: 466343 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0854. Min Act: -0.0004

Data Index: 65913 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0776. Min Act: -0.0004

Data Index: 1119855 (C4 (Web Text))

Max Activating Token Index: 789