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

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

Neuron 3248 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0825. Min Act: -0.0003

Data Index: 650899 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0762. Min Act: -0.0003

Data Index: 1265063 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0723. Min Act: -0.0003

Data Index: 1245485 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0773. Min Act: -0.0003

Data Index: 596925 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0686. Min Act: -0.0003

Data Index: 746136 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0672. Min Act: -0.0003

Data Index: 1213539 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0696. Min Act: -0.0003

Data Index: 113671 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0693. Min Act: -0.0003

Data Index: 1162050 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0712. Min Act: -0.0003

Data Index: 502954 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0708. Min Act: -0.0003

Data Index: 752125 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0683. Min Act: -0.0003

Data Index: 530657 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0680. Min Act: -0.0003

Data Index: 672987 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0704. Min Act: -0.0003

Data Index: 418256 (C4 (Web Text))

Max Activating Token Index: 390

Text #13

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0652. Min Act: -0.0003

Data Index: 236025 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1202113 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0692. Min Act: -0.0003

Data Index: 373264 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0658. Min Act: -0.0003

Data Index: 432690 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0632. Min Act: -0.0003

Data Index: 815473 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0643. Min Act: -0.0003

Data Index: 18129 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0631. Min Act: -0.0003

Data Index: 1340943 (C4 (Web Text))

Max Activating Token Index: 337