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

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

Neuron 3981 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: 0.8181. Min Range: -0.8181

Max Act: 0.8181. Min Act: -0.0000

Data Index: 1487459 (Python Code)

Max Activating Token Index: 306

Text #1

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1395864 (Python Code)

Max Activating Token Index: 627

Text #2

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6357. Min Act: -0.0000

Data Index: 1577863 (Python Code)

Max Activating Token Index: 364

Text #3

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5924. Min Act: -0.0000

Data Index: 1451823 (Python Code)

Max Activating Token Index: 579

Text #4

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1494560 (Python Code)

Max Activating Token Index: 420

Text #5

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1486581 (Python Code)

Max Activating Token Index: 205

Text #6

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6323. Min Act: -0.0000

Data Index: 1569760 (Python Code)

Max Activating Token Index: 592

Text #7

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1578128 (Python Code)

Max Activating Token Index: 101

Text #8

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5798. Min Act: -0.0001

Data Index: 1454548 (Python Code)

Max Activating Token Index: 342

Text #9

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1620574 (Python Code)

Max Activating Token Index: 592

Text #10

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1529874 (Python Code)

Max Activating Token Index: 169

Text #11

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.6395. Min Act: -0.0000

Data Index: 1543634 (Python Code)

Max Activating Token Index: 144

Text #12

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5550. Min Act: -0.0000

Data Index: 1371205 (Python Code)

Max Activating Token Index: 30

Text #13

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1601495 (Python Code)

Max Activating Token Index: 512

Text #14

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1390686 (Python Code)

Max Activating Token Index: 366

Text #15

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1436438 (Python Code)

Max Activating Token Index: 526

Text #16

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5368. Min Act: -0.0000

Data Index: 1564134 (Python Code)

Max Activating Token Index: 162

Text #17

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1496903 (Python Code)

Max Activating Token Index: 26

Text #18

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1588850 (Python Code)

Max Activating Token Index: 235

Text #19

Max Range: 0.8181. Min Range: -0.8181

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1445123 (Python Code)

Max Activating Token Index: 736