Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3745 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.1017. Min Act: -0.0001

Data Index: 1376810 (Python Code)

Max Activating Token Index: 767

Text #1

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0782. Min Act: -0.0001

Data Index: 1131706 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0773. Min Act: -0.0000

Data Index: 851197 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0786. Min Act: -0.0000

Data Index: 669089 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0758. Min Act: -0.0001

Data Index: 98452 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0774. Min Act: -0.0001

Data Index: 1453022 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0747. Min Act: -0.0001

Data Index: 937481 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0895. Min Act: -0.0000

Data Index: 477166 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1316346 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0653. Min Act: -0.0001

Data Index: 189512 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0648. Min Act: -0.0000

Data Index: 1630700 (Python Code)

Max Activating Token Index: 406

Text #11

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0637. Min Act: -0.0001

Data Index: 584084 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0675. Min Act: -0.0001

Data Index: 1562049 (Python Code)

Max Activating Token Index: 427

Text #13

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0650. Min Act: -0.0001

Data Index: 1223147 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0692. Min Act: -0.0001

Data Index: 878119 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0692. Min Act: -0.0001

Data Index: 618271 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0687. Min Act: -0.0001

Data Index: 1395899 (Python Code)

Max Activating Token Index: 670

Text #17

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0660. Min Act: -0.0001

Data Index: 1498801 (Python Code)

Max Activating Token Index: 85

Text #18

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0696. Min Act: -0.0001

Data Index: 407109 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.1017. Min Range: -0.1017

Max Act: 0.0621. Min Act: -0.0001

Data Index: 660326 (C4 (Web Text))

Max Activating Token Index: 563