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

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

Neuron 6088 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6637. Min Range: -3.6637

Max Act: 3.5313. Min Act: -0.0000

Data Index: 1463401 (Python Code)

Max Activating Token Index: 417

Text #1

Max Range: 3.6637. Min Range: -3.6637

Max Act: 3.6637. Min Act: -0.0000

Data Index: 1518489 (Python Code)

Max Activating Token Index: 790

Text #2

Max Range: 3.6637. Min Range: -3.6637

Max Act: 3.1737. Min Act: -0.0000

Data Index: 1486549 (Python Code)

Max Activating Token Index: 32

Text #3

Max Range: 3.6637. Min Range: -3.6637

Max Act: 3.2781. Min Act: -0.0000

Data Index: 1509827 (Python Code)

Max Activating Token Index: 994

Text #4

Max Range: 3.6637. Min Range: -3.6637

Max Act: 3.0217. Min Act: -0.0000

Data Index: 1542525 (Python Code)

Max Activating Token Index: 944

Text #5

Max Range: 3.6637. Min Range: -3.6637

Max Act: 2.9570. Min Act: -0.0000

Data Index: 1523370 (Python Code)

Max Activating Token Index: 1019

Text #6

Max Range: 3.6637. Min Range: -3.6637

Max Act: 3.0705. Min Act: -0.0000

Data Index: 1382098 (Python Code)

Max Activating Token Index: 503

Text #7

Max Range: 3.6637. Min Range: -3.6637

Max Act: 3.0530. Min Act: -0.0000

Data Index: 1464104 (Python Code)

Max Activating Token Index: 234

Text #8

Max Range: 3.6637. Min Range: -3.6637

Max Act: 2.8590. Min Act: -0.0000

Data Index: 1525386 (Python Code)

Max Activating Token Index: 72

Text #9

Max Range: 3.6637. Min Range: -3.6637

Max Act: 3.0055. Min Act: -0.0000

Data Index: 1362018 (Python Code)

Max Activating Token Index: 171

Text #10

Max Range: 3.6637. Min Range: -3.6637

Max Act: 2.9498. Min Act: -0.0000

Data Index: 1618761 (Python Code)

Max Activating Token Index: 808

Text #11

Max Range: 3.6637. Min Range: -3.6637

Max Act: 2.9368. Min Act: -0.0000

Data Index: 864604 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 3.6637. Min Range: -3.6637

Max Act: 2.8193. Min Act: -0.0000

Data Index: 1364937 (Python Code)

Max Activating Token Index: 81

Text #13

Max Range: 3.6637. Min Range: -3.6637

Max Act: 2.8163. Min Act: -0.0000

Data Index: 1476322 (Python Code)

Max Activating Token Index: 272

Text #14

Max Range: 3.6637. Min Range: -3.6637

Max Act: 2.8122. Min Act: -0.0000

Data Index: 1654876 (Python Code)

Max Activating Token Index: 227

Text #15

Max Range: 3.6637. Min Range: -3.6637

Max Act: 2.7918. Min Act: -0.0000

Data Index: 1560030 (Python Code)

Max Activating Token Index: 149

Text #16

Max Range: 3.6637. Min Range: -3.6637

Max Act: 2.6305. Min Act: -0.0000

Data Index: 1626998 (Python Code)

Max Activating Token Index: 211

Text #17

Max Range: 3.6637. Min Range: -3.6637

Max Act: 2.9657. Min Act: -0.0000

Data Index: 1636328 (Python Code)

Max Activating Token Index: 711

Text #18

Max Range: 3.6637. Min Range: -3.6637

Max Act: 2.8894. Min Act: -0.0000

Data Index: 1492032 (Python Code)

Max Activating Token Index: 758

Text #19

Max Range: 3.6637. Min Range: -3.6637

Max Act: 2.8624. Min Act: -0.0000

Data Index: 1442648 (Python Code)

Max Activating Token Index: 14