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

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

Neuron 25 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: 2.6290. Min Range: -2.6290

Max Act: 2.6290. Min Act: -0.0000

Data Index: 1584558 (Python Code)

Max Activating Token Index: 292

Text #1

Max Range: 2.6290. Min Range: -2.6290

Max Act: 2.3697. Min Act: -0.0000

Data Index: 1449390 (Python Code)

Max Activating Token Index: 905

Text #2

Max Range: 2.6290. Min Range: -2.6290

Max Act: 2.2015. Min Act: -0.0000

Data Index: 1257561 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 2.6290. Min Range: -2.6290

Max Act: 1.9767. Min Act: -0.0000

Data Index: 1640723 (Python Code)

Max Activating Token Index: 751

Text #4

Max Range: 2.6290. Min Range: -2.6290

Max Act: 2.1870. Min Act: -0.0000

Data Index: 1373057 (Python Code)

Max Activating Token Index: 223

Text #5

Max Range: 2.6290. Min Range: -2.6290

Max Act: 2.2094. Min Act: -0.0000

Data Index: 1479510 (Python Code)

Max Activating Token Index: 685

Text #6

Max Range: 2.6290. Min Range: -2.6290

Max Act: 2.2287. Min Act: -0.0000

Data Index: 1534492 (Python Code)

Max Activating Token Index: 677

Text #7

Max Range: 2.6290. Min Range: -2.6290

Max Act: 2.1106. Min Act: -0.0000

Data Index: 1548229 (Python Code)

Max Activating Token Index: 333

Text #8

Max Range: 2.6290. Min Range: -2.6290

Max Act: 1.9260. Min Act: -0.0000

Data Index: 1582409 (Python Code)

Max Activating Token Index: 757

Text #9

Max Range: 2.6290. Min Range: -2.6290

Max Act: 2.1420. Min Act: -0.0000

Data Index: 1285275 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 2.6290. Min Range: -2.6290

Max Act: 2.0191. Min Act: -0.0000

Data Index: 927735 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 2.6290. Min Range: -2.6290

Max Act: 1.9796. Min Act: -0.0000

Data Index: 1610602 (Python Code)

Max Activating Token Index: 282

Text #12

Max Range: 2.6290. Min Range: -2.6290

Max Act: 1.8757. Min Act: -0.0000

Data Index: 1644552 (Python Code)

Max Activating Token Index: 877

Text #13

Max Range: 2.6290. Min Range: -2.6290

Max Act: 1.9875. Min Act: -0.0000

Data Index: 1419031 (Python Code)

Max Activating Token Index: 530

Text #14

Max Range: 2.6290. Min Range: -2.6290

Max Act: 1.9786. Min Act: -0.0000

Data Index: 1421669 (Python Code)

Max Activating Token Index: 657

Text #15

Max Range: 2.6290. Min Range: -2.6290

Max Act: 1.9721. Min Act: -0.0000

Data Index: 1106110 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 2.6290. Min Range: -2.6290

Max Act: 2.0630. Min Act: -0.0000

Data Index: 1486171 (Python Code)

Max Activating Token Index: 380

Text #17

Max Range: 2.6290. Min Range: -2.6290

Max Act: 1.8576. Min Act: -0.0000

Data Index: 1448049 (Python Code)

Max Activating Token Index: 644

Text #18

Max Range: 2.6290. Min Range: -2.6290

Max Act: 1.8978. Min Act: -0.0000

Data Index: 1585009 (Python Code)

Max Activating Token Index: 437

Text #19

Max Range: 2.6290. Min Range: -2.6290

Max Act: 1.7962. Min Act: -0.0000

Data Index: 1456772 (Python Code)

Max Activating Token Index: 640