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

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

Neuron 3842 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6911. Min Act: -0.0001

Data Index: 1556856 (Python Code)

Max Activating Token Index: 130

Text #1

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5574. Min Act: -0.0001

Data Index: 1384465 (Python Code)

Max Activating Token Index: 847

Text #2

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6915. Min Act: -0.0001

Data Index: 1509557 (Python Code)

Max Activating Token Index: 149

Text #3

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5973. Min Act: -0.0001

Data Index: 1642010 (Python Code)

Max Activating Token Index: 988

Text #4

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5635. Min Act: -0.0001

Data Index: 1550898 (Python Code)

Max Activating Token Index: 748

Text #5

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6092. Min Act: -0.0001

Data Index: 1545375 (Python Code)

Max Activating Token Index: 992

Text #6

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5924. Min Act: -0.0001

Data Index: 1552142 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6244. Min Act: -0.0001

Data Index: 1462553 (Python Code)

Max Activating Token Index: 478

Text #8

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6364. Min Act: -0.0001

Data Index: 1404281 (Python Code)

Max Activating Token Index: 423

Text #9

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5258. Min Act: -0.0001

Data Index: 1617249 (Python Code)

Max Activating Token Index: 274

Text #10

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6379. Min Act: -0.0001

Data Index: 1589507 (Python Code)

Max Activating Token Index: 579

Text #11

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5387. Min Act: -0.0001

Data Index: 1545764 (Python Code)

Max Activating Token Index: 531

Text #12

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5137. Min Act: -0.0001

Data Index: 1500094 (Python Code)

Max Activating Token Index: 195

Text #13

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5506. Min Act: -0.0001

Data Index: 1570802 (Python Code)

Max Activating Token Index: 107

Text #14

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5653. Min Act: -0.0001

Data Index: 1461764 (Python Code)

Max Activating Token Index: 85

Text #15

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5727. Min Act: -0.0001

Data Index: 1370539 (Python Code)

Max Activating Token Index: 654

Text #16

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5751. Min Act: -0.0001

Data Index: 1375082 (Python Code)

Max Activating Token Index: 647

Text #17

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5428. Min Act: -0.0001

Data Index: 1369548 (Python Code)

Max Activating Token Index: 906

Text #18

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5245. Min Act: -0.0001

Data Index: 1423610 (Python Code)

Max Activating Token Index: 997

Text #19

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.4949. Min Act: -0.0001

Data Index: 1371097 (Python Code)

Max Activating Token Index: 128