Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 309 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0774. Min Act: -0.0002

Data Index: 96507 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1066390 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0752. Min Act: -0.0002

Data Index: 804288 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0805. Min Act: -0.0002

Data Index: 613378 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1099063 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0766. Min Act: -0.0002

Data Index: 44935 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1184130 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0705. Min Act: -0.0002

Data Index: 268571 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0776. Min Act: -0.0002

Data Index: 184249 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0768. Min Act: -0.0002

Data Index: 580669 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0715. Min Act: -0.0002

Data Index: 364921 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0645. Min Act: -0.0002

Data Index: 598638 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0716. Min Act: -0.0002

Data Index: 234569 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1329443 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0709. Min Act: -0.0002

Data Index: 197649 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1066982 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1214733 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0685. Min Act: -0.0002

Data Index: 322979 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0701. Min Act: -0.0002

Data Index: 986152 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1082007 (C4 (Web Text))

Max Activating Token Index: 580