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

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

Neuron 120 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9004. Min Range: -2.9004

Max Act: 2.8145. Min Act: -0.0000

Data Index: 1179505 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 2.9004. Min Range: -2.9004

Max Act: 2.9004. Min Act: -0.0000

Data Index: 1281388 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 2.9004. Min Range: -2.9004

Max Act: 2.8832. Min Act: -0.0000

Data Index: 41841 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 2.9004. Min Range: -2.9004

Max Act: 2.4779. Min Act: -0.0000

Data Index: 315381 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 2.9004. Min Range: -2.9004

Max Act: 2.5540. Min Act: -0.0000

Data Index: 1077363 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 2.9004. Min Range: -2.9004

Max Act: 2.2661. Min Act: -0.0000

Data Index: 77344 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 2.9004. Min Range: -2.9004

Max Act: 2.0389. Min Act: -0.0000

Data Index: 1326019 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 2.9004. Min Range: -2.9004

Max Act: 2.0500. Min Act: -0.0000

Data Index: 128325 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 2.9004. Min Range: -2.9004

Max Act: 1.7969. Min Act: -0.0000

Data Index: 260032 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 2.9004. Min Range: -2.9004

Max Act: 1.9878. Min Act: -0.0000

Data Index: 1141497 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 2.9004. Min Range: -2.9004

Max Act: 1.9266. Min Act: -0.0000

Data Index: 1300525 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 2.9004. Min Range: -2.9004

Max Act: 2.0085. Min Act: 0.0000

Data Index: 207186 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 2.9004. Min Range: -2.9004

Max Act: 1.9092. Min Act: -0.0000

Data Index: 745183 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 2.9004. Min Range: -2.9004

Max Act: 1.9902. Min Act: 0.0000

Data Index: 646898 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 2.9004. Min Range: -2.9004

Max Act: 1.8719. Min Act: -0.0000

Data Index: 387614 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 2.9004. Min Range: -2.9004

Max Act: 1.8087. Min Act: -0.0000

Data Index: 1270017 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 2.9004. Min Range: -2.9004

Max Act: 1.7677. Min Act: -0.0000

Data Index: 1208760 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 2.9004. Min Range: -2.9004

Max Act: 1.8417. Min Act: -0.0000

Data Index: 1308076 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 2.9004. Min Range: -2.9004

Max Act: 1.7635. Min Act: -0.0000

Data Index: 662432 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 2.9004. Min Range: -2.9004

Max Act: 1.7394. Min Act: -0.0000

Data Index: 1100029 (C4 (Web Text))

Max Activating Token Index: 374