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

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

Neuron 1032 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: 0.0889. Min Range: -0.0889

Max Act: 0.0889. Min Act: -0.0003

Data Index: 87904 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0802. Min Act: -0.0003

Data Index: 944657 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0761. Min Act: -0.0003

Data Index: 752056 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0750. Min Act: -0.0003

Data Index: 548488 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0745. Min Act: -0.0003

Data Index: 410345 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0724. Min Act: -0.0003

Data Index: 87988 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0711. Min Act: -0.0003

Data Index: 879515 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1172353 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0694. Min Act: -0.0002

Data Index: 1010407 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0677. Min Act: -0.0003

Data Index: 399607 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0675. Min Act: -0.0003

Data Index: 922676 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0697. Min Act: -0.0003

Data Index: 150681 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0666. Min Act: -0.0003

Data Index: 1154307 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0640. Min Act: -0.0003

Data Index: 1180987 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0656. Min Act: -0.0003

Data Index: 617274 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0636. Min Act: -0.0003

Data Index: 179467 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0631. Min Act: -0.0003

Data Index: 944625 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0631. Min Act: -0.0003

Data Index: 531318 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0613. Min Act: -0.0003

Data Index: 873699 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0644. Min Act: -0.0003

Data Index: 799609 (C4 (Web Text))

Max Activating Token Index: 732