Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3690 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.4427. Min Act: -0.0000

Data Index: 881605 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3998. Min Act: -0.0000

Data Index: 179400 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3967. Min Act: -0.0001

Data Index: 146440 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.4201. Min Act: -0.0001

Data Index: 298607 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3809. Min Act: -0.0000

Data Index: 687819 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3585. Min Act: -0.0000

Data Index: 744718 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3833. Min Act: -0.0000

Data Index: 735350 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3688. Min Act: -0.0001

Data Index: 891526 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3839. Min Act: -0.0001

Data Index: 1161101 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3812. Min Act: -0.0001

Data Index: 806716 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3539. Min Act: -0.0000

Data Index: 390200 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3766. Min Act: -0.0001

Data Index: 184997 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3619. Min Act: -0.0000

Data Index: 318645 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3452. Min Act: -0.0000

Data Index: 417664 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1314359 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3590. Min Act: -0.0000

Data Index: 155241 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3581. Min Act: -0.0000

Data Index: 612813 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3773. Min Act: -0.0001

Data Index: 1006904 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3580. Min Act: -0.0001

Data Index: 1092653 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3434. Min Act: -0.0001

Data Index: 338479 (C4 (Web Text))

Max Activating Token Index: 265