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

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

Neuron 1741 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0683. Min Range: -5.0683

Max Act: 5.0683. Min Act: -0.0002

Data Index: 1478743 (Python Code)

Max Activating Token Index: 203

Text #1

Max Range: 5.0683. Min Range: -5.0683

Max Act: 5.0604. Min Act: -0.0002

Data Index: 1503645 (Python Code)

Max Activating Token Index: 865

Text #2

Max Range: 5.0683. Min Range: -5.0683

Max Act: 3.8604. Min Act: -0.0002

Data Index: 1620266 (Python Code)

Max Activating Token Index: 225

Text #3

Max Range: 5.0683. Min Range: -5.0683

Max Act: 4.6195. Min Act: -0.0002

Data Index: 1486604 (Python Code)

Max Activating Token Index: 400

Text #4

Max Range: 5.0683. Min Range: -5.0683

Max Act: 3.5444. Min Act: -0.0002

Data Index: 1367506 (Python Code)

Max Activating Token Index: 576

Text #5

Max Range: 5.0683. Min Range: -5.0683

Max Act: 3.5739. Min Act: -0.0002

Data Index: 1637803 (Python Code)

Max Activating Token Index: 108

Text #6

Max Range: 5.0683. Min Range: -5.0683

Max Act: 4.5495. Min Act: -0.0002

Data Index: 1571119 (Python Code)

Max Activating Token Index: 341

Text #7

Max Range: 5.0683. Min Range: -5.0683

Max Act: 3.4551. Min Act: -0.0002

Data Index: 1480613 (Python Code)

Max Activating Token Index: 155

Text #8

Max Range: 5.0683. Min Range: -5.0683

Max Act: 4.2877. Min Act: -0.0002

Data Index: 1410952 (Python Code)

Max Activating Token Index: 632

Text #9

Max Range: 5.0683. Min Range: -5.0683

Max Act: 3.4271. Min Act: -0.0002

Data Index: 1403813 (Python Code)

Max Activating Token Index: 210

Text #10

Max Range: 5.0683. Min Range: -5.0683

Max Act: 4.2735. Min Act: -0.0002

Data Index: 1645763 (Python Code)

Max Activating Token Index: 276

Text #11

Max Range: 5.0683. Min Range: -5.0683

Max Act: 3.1570. Min Act: -0.0002

Data Index: 1590860 (Python Code)

Max Activating Token Index: 301

Text #12

Max Range: 5.0683. Min Range: -5.0683

Max Act: 3.5871. Min Act: -0.0002

Data Index: 1608232 (Python Code)

Max Activating Token Index: 276

Text #13

Max Range: 5.0683. Min Range: -5.0683

Max Act: 3.7160. Min Act: -0.0002

Data Index: 1646518 (Python Code)

Max Activating Token Index: 240

Text #14

Max Range: 5.0683. Min Range: -5.0683

Max Act: 3.8364. Min Act: -0.0002

Data Index: 1570453 (Python Code)

Max Activating Token Index: 211

Text #15

Max Range: 5.0683. Min Range: -5.0683

Max Act: 3.6226. Min Act: -0.0002

Data Index: 1586689 (Python Code)

Max Activating Token Index: 169

Text #16

Max Range: 5.0683. Min Range: -5.0683

Max Act: 3.2023. Min Act: -0.0002

Data Index: 1562653 (Python Code)

Max Activating Token Index: 386

Text #17

Max Range: 5.0683. Min Range: -5.0683

Max Act: 3.7643. Min Act: -0.0002

Data Index: 1644294 (Python Code)

Max Activating Token Index: 861

Text #18

Max Range: 5.0683. Min Range: -5.0683

Max Act: 3.7296. Min Act: -0.0002

Data Index: 1652799 (Python Code)

Max Activating Token Index: 477

Text #19

Max Range: 5.0683. Min Range: -5.0683

Max Act: 3.4352. Min Act: -0.0002

Data Index: 1390756 (Python Code)

Max Activating Token Index: 246