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

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

Neuron 2349 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1700. Min Range: -1.1700

Max Act: 1.1651. Min Act: -0.0000

Data Index: 1523040 (Python Code)

Max Activating Token Index: 817

Text #1

Max Range: 1.1700. Min Range: -1.1700

Max Act: 1.1700. Min Act: -0.0000

Data Index: 1655403 (Python Code)

Max Activating Token Index: 545

Text #2

Max Range: 1.1700. Min Range: -1.1700

Max Act: 1.0743. Min Act: -0.0000

Data Index: 1580518 (Python Code)

Max Activating Token Index: 294

Text #3

Max Range: 1.1700. Min Range: -1.1700

Max Act: 1.0204. Min Act: -0.0000

Data Index: 1613487 (Python Code)

Max Activating Token Index: 824

Text #4

Max Range: 1.1700. Min Range: -1.1700

Max Act: 1.0308. Min Act: -0.0000

Data Index: 1587279 (Python Code)

Max Activating Token Index: 342

Text #5

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.9551. Min Act: -0.0000

Data Index: 1632119 (Python Code)

Max Activating Token Index: 489

Text #6

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.9464. Min Act: -0.0000

Data Index: 1513359 (Python Code)

Max Activating Token Index: 356

Text #7

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.9677. Min Act: -0.0000

Data Index: 1368400 (Python Code)

Max Activating Token Index: 453

Text #8

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.9757. Min Act: -0.0000

Data Index: 1504364 (Python Code)

Max Activating Token Index: 795

Text #9

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8866. Min Act: -0.0000

Data Index: 1514903 (Python Code)

Max Activating Token Index: 318

Text #10

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.9908. Min Act: -0.0000

Data Index: 1399247 (Python Code)

Max Activating Token Index: 318

Text #11

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8809. Min Act: -0.0000

Data Index: 1569185 (Python Code)

Max Activating Token Index: 296

Text #12

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.9545. Min Act: -0.0000

Data Index: 1576430 (Python Code)

Max Activating Token Index: 712

Text #13

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.9533. Min Act: -0.0000

Data Index: 1453978 (Python Code)

Max Activating Token Index: 76

Text #14

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8692. Min Act: -0.0000

Data Index: 1436258 (Python Code)

Max Activating Token Index: 88

Text #15

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.9788. Min Act: -0.0000

Data Index: 1401658 (Python Code)

Max Activating Token Index: 594

Text #16

Max Range: 1.1700. Min Range: -1.1700

Max Act: 1.0012. Min Act: -0.0001

Data Index: 1465790 (Python Code)

Max Activating Token Index: 831

Text #17

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8890. Min Act: -0.0000

Data Index: 1524437 (Python Code)

Max Activating Token Index: 568

Text #18

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8489. Min Act: -0.0000

Data Index: 1644743 (Python Code)

Max Activating Token Index: 480

Text #19

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8804. Min Act: -0.0000

Data Index: 1560968 (Python Code)

Max Activating Token Index: 256