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

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

Neuron 3052 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: 2.6229. Min Range: -2.6229

Max Act: 2.4424. Min Act: -0.0000

Data Index: 1592206 (Python Code)

Max Activating Token Index: 484

Text #1

Max Range: 2.6229. Min Range: -2.6229

Max Act: 2.6229. Min Act: -0.0000

Data Index: 1624575 (Python Code)

Max Activating Token Index: 86

Text #2

Max Range: 2.6229. Min Range: -2.6229

Max Act: 2.3746. Min Act: -0.0000

Data Index: 1415168 (Python Code)

Max Activating Token Index: 981

Text #3

Max Range: 2.6229. Min Range: -2.6229

Max Act: 2.0481. Min Act: -0.0000

Data Index: 1601046 (Python Code)

Max Activating Token Index: 618

Text #4

Max Range: 2.6229. Min Range: -2.6229

Max Act: 2.2854. Min Act: -0.0000

Data Index: 1618772 (Python Code)

Max Activating Token Index: 860

Text #5

Max Range: 2.6229. Min Range: -2.6229

Max Act: 2.1738. Min Act: -0.0000

Data Index: 1460995 (Python Code)

Max Activating Token Index: 434

Text #6

Max Range: 2.6229. Min Range: -2.6229

Max Act: 2.0538. Min Act: -0.0000

Data Index: 1629525 (Python Code)

Max Activating Token Index: 303

Text #7

Max Range: 2.6229. Min Range: -2.6229

Max Act: 1.8693. Min Act: -0.0000

Data Index: 1495607 (Python Code)

Max Activating Token Index: 866

Text #8

Max Range: 2.6229. Min Range: -2.6229

Max Act: 2.0155. Min Act: -0.0000

Data Index: 1517788 (Python Code)

Max Activating Token Index: 426

Text #9

Max Range: 2.6229. Min Range: -2.6229

Max Act: 1.9367. Min Act: -0.0000

Data Index: 1546806 (Python Code)

Max Activating Token Index: 107

Text #10

Max Range: 2.6229. Min Range: -2.6229

Max Act: 2.0352. Min Act: -0.0000

Data Index: 1470201 (Python Code)

Max Activating Token Index: 244

Text #11

Max Range: 2.6229. Min Range: -2.6229

Max Act: 2.0308. Min Act: -0.0000

Data Index: 1538039 (Python Code)

Max Activating Token Index: 290

Text #12

Max Range: 2.6229. Min Range: -2.6229

Max Act: 1.9480. Min Act: -0.0000

Data Index: 1571861 (Python Code)

Max Activating Token Index: 80

Text #13

Max Range: 2.6229. Min Range: -2.6229

Max Act: 1.8233. Min Act: -0.0000

Data Index: 1365003 (Python Code)

Max Activating Token Index: 388

Text #14

Max Range: 2.6229. Min Range: -2.6229

Max Act: 1.7984. Min Act: -0.0000

Data Index: 1522200 (Python Code)

Max Activating Token Index: 934

Text #15

Max Range: 2.6229. Min Range: -2.6229

Max Act: 1.8366. Min Act: -0.0000

Data Index: 1429257 (Python Code)

Max Activating Token Index: 159

Text #16

Max Range: 2.6229. Min Range: -2.6229

Max Act: 1.9733. Min Act: -0.0000

Data Index: 1650546 (Python Code)

Max Activating Token Index: 264

Text #17

Max Range: 2.6229. Min Range: -2.6229

Max Act: 1.9327. Min Act: -0.0000

Data Index: 1609868 (Python Code)

Max Activating Token Index: 326

Text #18

Max Range: 2.6229. Min Range: -2.6229

Max Act: 1.8529. Min Act: -0.0000

Data Index: 1451933 (Python Code)

Max Activating Token Index: 315

Text #19

Max Range: 2.6229. Min Range: -2.6229

Max Act: 1.8394. Min Act: -0.0000

Data Index: 1595734 (Python Code)

Max Activating Token Index: 451