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

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

Neuron 5675 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.7780. Min Act: -0.0000

Data Index: 1464202 (Python Code)

Max Activating Token Index: 758

Text #1

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1606121 (Python Code)

Max Activating Token Index: 638

Text #2

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.7285. Min Act: -0.0000

Data Index: 1550494 (Python Code)

Max Activating Token Index: 485

Text #3

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6792. Min Act: -0.0000

Data Index: 1370324 (Python Code)

Max Activating Token Index: 361

Text #4

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1623340 (Python Code)

Max Activating Token Index: 265

Text #5

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1595131 (Python Code)

Max Activating Token Index: 412

Text #6

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6549. Min Act: -0.0000

Data Index: 1417999 (Python Code)

Max Activating Token Index: 781

Text #7

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1436262 (Python Code)

Max Activating Token Index: 496

Text #8

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6263. Min Act: -0.0000

Data Index: 1530788 (Python Code)

Max Activating Token Index: 968

Text #9

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1542469 (Python Code)

Max Activating Token Index: 171

Text #10

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6025. Min Act: -0.0000

Data Index: 1576880 (Python Code)

Max Activating Token Index: 283

Text #11

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1428576 (Python Code)

Max Activating Token Index: 301

Text #12

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5943. Min Act: -0.0000

Data Index: 1390121 (Python Code)

Max Activating Token Index: 142

Text #13

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5779. Min Act: -0.0000

Data Index: 1633141 (Python Code)

Max Activating Token Index: 74

Text #14

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1485057 (Python Code)

Max Activating Token Index: 152

Text #15

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.6029. Min Act: -0.0000

Data Index: 1452098 (Python Code)

Max Activating Token Index: 448

Text #16

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1648528 (Python Code)

Max Activating Token Index: 430

Text #17

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5918. Min Act: -0.0000

Data Index: 1366738 (Python Code)

Max Activating Token Index: 387

Text #18

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5719. Min Act: -0.0000

Data Index: 1510331 (Python Code)

Max Activating Token Index: 246

Text #19

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5705. Min Act: -0.0000

Data Index: 1595920 (Python Code)

Max Activating Token Index: 960