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

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

Neuron 5198 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4863. Min Range: -2.4863

Max Act: 2.0731. Min Act: -0.0000

Data Index: 1495377 (Python Code)

Max Activating Token Index: 330

Text #1

Max Range: 2.4863. Min Range: -2.4863

Max Act: 2.4863. Min Act: -0.0001

Data Index: 1535297 (Python Code)

Max Activating Token Index: 76

Text #2

Max Range: 2.4863. Min Range: -2.4863

Max Act: 2.4326. Min Act: -0.0000

Data Index: 1556375 (Python Code)

Max Activating Token Index: 393

Text #3

Max Range: 2.4863. Min Range: -2.4863

Max Act: 2.2039. Min Act: -0.0000

Data Index: 1485851 (Python Code)

Max Activating Token Index: 310

Text #4

Max Range: 2.4863. Min Range: -2.4863

Max Act: 2.1172. Min Act: -0.0000

Data Index: 1556456 (Python Code)

Max Activating Token Index: 620

Text #5

Max Range: 2.4863. Min Range: -2.4863

Max Act: 2.0938. Min Act: -0.0000

Data Index: 1498532 (Python Code)

Max Activating Token Index: 616

Text #6

Max Range: 2.4863. Min Range: -2.4863

Max Act: 2.0770. Min Act: -0.0000

Data Index: 1622337 (Python Code)

Max Activating Token Index: 654

Text #7

Max Range: 2.4863. Min Range: -2.4863

Max Act: 1.9244. Min Act: -0.0000

Data Index: 1466591 (Python Code)

Max Activating Token Index: 275

Text #8

Max Range: 2.4863. Min Range: -2.4863

Max Act: 1.8686. Min Act: -0.0000

Data Index: 1616256 (Python Code)

Max Activating Token Index: 366

Text #9

Max Range: 2.4863. Min Range: -2.4863

Max Act: 1.8276. Min Act: -0.0001

Data Index: 1442527 (Python Code)

Max Activating Token Index: 483

Text #10

Max Range: 2.4863. Min Range: -2.4863

Max Act: 1.6534. Min Act: -0.0001

Data Index: 1639406 (Python Code)

Max Activating Token Index: 284

Text #11

Max Range: 2.4863. Min Range: -2.4863

Max Act: 1.9837. Min Act: -0.0001

Data Index: 1492705 (Python Code)

Max Activating Token Index: 96

Text #12

Max Range: 2.4863. Min Range: -2.4863

Max Act: 1.8818. Min Act: -0.0000

Data Index: 1431607 (Python Code)

Max Activating Token Index: 533

Text #13

Max Range: 2.4863. Min Range: -2.4863

Max Act: 1.8530. Min Act: -0.0000

Data Index: 1443530 (Python Code)

Max Activating Token Index: 58

Text #14

Max Range: 2.4863. Min Range: -2.4863

Max Act: 1.8395. Min Act: -0.0001

Data Index: 1480667 (Python Code)

Max Activating Token Index: 14

Text #15

Max Range: 2.4863. Min Range: -2.4863

Max Act: 1.6824. Min Act: -0.0001

Data Index: 1620234 (Python Code)

Max Activating Token Index: 467

Text #16

Max Range: 2.4863. Min Range: -2.4863

Max Act: 1.8197. Min Act: -0.0000

Data Index: 1622383 (Python Code)

Max Activating Token Index: 249

Text #17

Max Range: 2.4863. Min Range: -2.4863

Max Act: 1.7385. Min Act: -0.0000

Data Index: 1601978 (Python Code)

Max Activating Token Index: 267

Text #18

Max Range: 2.4863. Min Range: -2.4863

Max Act: 1.8013. Min Act: -0.0001

Data Index: 1389650 (Python Code)

Max Activating Token Index: 48

Text #19

Max Range: 2.4863. Min Range: -2.4863

Max Act: 1.7856. Min Act: -0.0001

Data Index: 1362920 (Python Code)

Max Activating Token Index: 784