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

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

Neuron 5826 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: 0.1065. Min Range: -0.1065

Max Act: 0.1065. Min Act: -0.0002

Data Index: 793274 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0923. Min Act: -0.0002

Data Index: 1145289 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1075007 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0837. Min Act: -0.0002

Data Index: 720338 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0823. Min Act: -0.0002

Data Index: 807390 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0850. Min Act: -0.0002

Data Index: 218855 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0839. Min Act: -0.0002

Data Index: 897992 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0865. Min Act: -0.0002

Data Index: 684619 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0836. Min Act: -0.0002

Data Index: 1058473 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0801. Min Act: -0.0002

Data Index: 371850 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1150919 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0819. Min Act: -0.0002

Data Index: 449696 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1346006 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0768. Min Act: -0.0002

Data Index: 222849 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1010371 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0732. Min Act: -0.0002

Data Index: 156636 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0706. Min Act: -0.0002

Data Index: 1101619 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0726. Min Act: -0.0002

Data Index: 895117 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0728. Min Act: -0.0002

Data Index: 58734 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0686. Min Act: -0.0002

Data Index: 795555 (C4 (Web Text))

Max Activating Token Index: 254