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

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

Neuron 4954 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6985. Min Range: -1.6985

Max Act: 1.6985. Min Act: -0.0000

Data Index: 1567933 (Python Code)

Max Activating Token Index: 805

Text #1

Max Range: 1.6985. Min Range: -1.6985

Max Act: 1.6460. Min Act: -0.0000

Data Index: 1568805 (Python Code)

Max Activating Token Index: 780

Text #2

Max Range: 1.6985. Min Range: -1.6985

Max Act: 1.6346. Min Act: -0.0000

Data Index: 1419261 (Python Code)

Max Activating Token Index: 397

Text #3

Max Range: 1.6985. Min Range: -1.6985

Max Act: 1.4688. Min Act: -0.0000

Data Index: 1369895 (Python Code)

Max Activating Token Index: 885

Text #4

Max Range: 1.6985. Min Range: -1.6985

Max Act: 1.5437. Min Act: -0.0000

Data Index: 44411 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 1.6985. Min Range: -1.6985

Max Act: 1.4895. Min Act: -0.0000

Data Index: 1307244 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 1.6985. Min Range: -1.6985

Max Act: 1.3701. Min Act: -0.0000

Data Index: 5398 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 1.6985. Min Range: -1.6985

Max Act: 1.4209. Min Act: -0.0000

Data Index: 1377560 (Python Code)

Max Activating Token Index: 156

Text #8

Max Range: 1.6985. Min Range: -1.6985

Max Act: 1.3025. Min Act: -0.0000

Data Index: 1085422 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 1.6985. Min Range: -1.6985

Max Act: 1.3860. Min Act: -0.0000

Data Index: 1556224 (Python Code)

Max Activating Token Index: 821

Text #10

Max Range: 1.6985. Min Range: -1.6985

Max Act: 1.2780. Min Act: -0.0000

Data Index: 1479633 (Python Code)

Max Activating Token Index: 174

Text #11

Max Range: 1.6985. Min Range: -1.6985

Max Act: 1.2909. Min Act: -0.0000

Data Index: 593886 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 1.6985. Min Range: -1.6985

Max Act: 1.2729. Min Act: -0.0000

Data Index: 464590 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 1.6985. Min Range: -1.6985

Max Act: 1.1940. Min Act: -0.0000

Data Index: 576460 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 1.6985. Min Range: -1.6985

Max Act: 1.2742. Min Act: -0.0000

Data Index: 772562 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 1.6985. Min Range: -1.6985

Max Act: 1.2867. Min Act: -0.0000

Data Index: 1478458 (Python Code)

Max Activating Token Index: 737

Text #16

Max Range: 1.6985. Min Range: -1.6985

Max Act: 1.2897. Min Act: -0.0000

Data Index: 1402370 (Python Code)

Max Activating Token Index: 199

Text #17

Max Range: 1.6985. Min Range: -1.6985

Max Act: 1.2217. Min Act: -0.0000

Data Index: 1585407 (Python Code)

Max Activating Token Index: 833

Text #18

Max Range: 1.6985. Min Range: -1.6985

Max Act: 1.1768. Min Act: -0.0000

Data Index: 1124915 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 1.6985. Min Range: -1.6985

Max Act: 1.2184. Min Act: -0.0000

Data Index: 55844 (C4 (Web Text))

Max Activating Token Index: 951