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

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

Neuron 1549 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.5558. Min Act: -0.0000

Data Index: 1442720 (Python Code)

Max Activating Token Index: 164

Text #1

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.5557. Min Act: -0.0000

Data Index: 348394 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.5346. Min Act: -0.0000

Data Index: 1372632 (Python Code)

Max Activating Token Index: 1021

Text #3

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1473689 (Python Code)

Max Activating Token Index: 353

Text #4

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1604591 (Python Code)

Max Activating Token Index: 714

Text #5

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1490083 (Python Code)

Max Activating Token Index: 959

Text #6

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4717. Min Act: -0.0000

Data Index: 1541429 (Python Code)

Max Activating Token Index: 663

Text #7

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1545882 (Python Code)

Max Activating Token Index: 969

Text #8

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4719. Min Act: -0.0000

Data Index: 1291848 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1509867 (Python Code)

Max Activating Token Index: 776

Text #10

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4365. Min Act: -0.0000

Data Index: 641810 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1394622 (Python Code)

Max Activating Token Index: 777

Text #12

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4184. Min Act: -0.0000

Data Index: 892188 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4288. Min Act: -0.0000

Data Index: 1477506 (Python Code)

Max Activating Token Index: 560

Text #14

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1390321 (Python Code)

Max Activating Token Index: 868

Text #15

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4424. Min Act: -0.0000

Data Index: 547946 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4536. Min Act: -0.0000

Data Index: 9736 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4251. Min Act: -0.0000

Data Index: 282977 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1244466 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4341. Min Act: -0.0000

Data Index: 516483 (C4 (Web Text))

Max Activating Token Index: 17