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

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

Neuron 13 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2876. Min Act: -0.0000

Data Index: 1177050 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.3083. Min Act: -0.0000

Data Index: 283654 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2723. Min Act: -0.0000

Data Index: 1325335 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2819. Min Act: -0.0000

Data Index: 356863 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2615. Min Act: -0.0000

Data Index: 605078 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1230752 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1139913 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1988. Min Act: -0.0000

Data Index: 846294 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1750. Min Act: -0.0000

Data Index: 129676 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1897. Min Act: -0.0000

Data Index: 245985 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1088810 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1715. Min Act: -0.0000

Data Index: 649429 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1690. Min Act: -0.0000

Data Index: 774287 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1556. Min Act: -0.0000

Data Index: 1170057 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1720. Min Act: -0.0000

Data Index: 720947 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1681. Min Act: -0.0000

Data Index: 555626 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1486. Min Act: -0.0000

Data Index: 900206 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1358639 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1476. Min Act: -0.0000

Data Index: 31385 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1565. Min Act: -0.0000

Data Index: 158376 (C4 (Web Text))

Max Activating Token Index: 46