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

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

Neuron 3543 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: 0.0757. Min Range: -0.0757

Max Act: 0.0757. Min Act: -0.0003

Data Index: 607030 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0739. Min Act: -0.0003

Data Index: 898020 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1061145 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0643. Min Act: -0.0003

Data Index: 801465 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1130645 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0590. Min Act: -0.0002

Data Index: 65699 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0569. Min Act: -0.0003

Data Index: 41891 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0572. Min Act: -0.0003

Data Index: 674882 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0560. Min Act: -0.0003

Data Index: 734673 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0565. Min Act: -0.0002

Data Index: 861866 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0525. Min Act: -0.0002

Data Index: 823721 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0506. Min Act: -0.0002

Data Index: 377514 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0509. Min Act: -0.0003

Data Index: 347203 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0507. Min Act: -0.0003

Data Index: 585941 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0530. Min Act: -0.0002

Data Index: 690477 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1008722 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1087947 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1386893 (Python Code)

Max Activating Token Index: 258

Text #18

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0487. Min Act: -0.0002

Data Index: 328294 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1026384 (C4 (Web Text))

Max Activating Token Index: 196