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

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

Neuron 5471 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3888. Min Range: -2.3888

Max Act: 2.3888. Min Act: -0.0000

Data Index: 1347483 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 2.3888. Min Range: -2.3888

Max Act: 2.3541. Min Act: -0.0000

Data Index: 151895 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 2.3888. Min Range: -2.3888

Max Act: 2.0998. Min Act: 0.0002

Data Index: 1063152 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 2.3888. Min Range: -2.3888

Max Act: 1.9382. Min Act: -0.0000

Data Index: 905068 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 2.3888. Min Range: -2.3888

Max Act: 1.9752. Min Act: -0.0000

Data Index: 810993 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 2.3888. Min Range: -2.3888

Max Act: 1.9838. Min Act: -0.0000

Data Index: 454007 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 2.3888. Min Range: -2.3888

Max Act: 2.0728. Min Act: -0.0000

Data Index: 905962 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 2.3888. Min Range: -2.3888

Max Act: 1.8867. Min Act: -0.0000

Data Index: 866904 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 2.3888. Min Range: -2.3888

Max Act: 1.8775. Min Act: -0.0000

Data Index: 991783 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 2.3888. Min Range: -2.3888

Max Act: 1.9405. Min Act: 0.0002

Data Index: 1085459 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 2.3888. Min Range: -2.3888

Max Act: 1.8249. Min Act: -0.0000

Data Index: 331139 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 2.3888. Min Range: -2.3888

Max Act: 1.6794. Min Act: 0.0002

Data Index: 1119426 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 2.3888. Min Range: -2.3888

Max Act: 1.6689. Min Act: -0.0000

Data Index: 855660 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 2.3888. Min Range: -2.3888

Max Act: 1.6831. Min Act: -0.0000

Data Index: 7435 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 2.3888. Min Range: -2.3888

Max Act: 1.6564. Min Act: 0.0001

Data Index: 328148 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 2.3888. Min Range: -2.3888

Max Act: 1.5719. Min Act: -0.0000

Data Index: 140577 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 2.3888. Min Range: -2.3888

Max Act: 1.5714. Min Act: -0.0000

Data Index: 1162465 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 2.3888. Min Range: -2.3888

Max Act: 1.5401. Min Act: -0.0000

Data Index: 115187 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 2.3888. Min Range: -2.3888

Max Act: 1.6270. Min Act: -0.0000

Data Index: 705646 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 2.3888. Min Range: -2.3888

Max Act: 1.5977. Min Act: -0.0000

Data Index: 98278 (C4 (Web Text))

Max Activating Token Index: 334