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

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

Neuron 1814 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: 0.0677. Min Range: -0.0677

Max Act: 0.0659. Min Act: -0.0002

Data Index: 221818 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1101909 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0677. Min Act: -0.0002

Data Index: 259609 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0606. Min Act: -0.0002

Data Index: 927477 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1003955 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0556. Min Act: -0.0002

Data Index: 987856 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1017781 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0637. Min Act: -0.0002

Data Index: 711667 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0573. Min Act: -0.0002

Data Index: 699268 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0632. Min Act: -0.0002

Data Index: 350586 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0586. Min Act: -0.0002

Data Index: 577016 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0558. Min Act: -0.0002

Data Index: 98550 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1163703 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0592. Min Act: -0.0002

Data Index: 731598 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1451989 (Python Code)

Max Activating Token Index: 886

Text #15

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1174936 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0559. Min Act: -0.0002

Data Index: 622802 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0582. Min Act: -0.0002

Data Index: 370516 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0562. Min Act: -0.0002

Data Index: 985631 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1342565 (C4 (Web Text))

Max Activating Token Index: 625