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

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

Neuron 3859 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: 0.8273. Min Range: -0.8273

Max Act: 0.6829. Min Act: -0.0002

Data Index: 1605621 (Python Code)

Max Activating Token Index: 184

Text #1

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.7171. Min Act: -0.0002

Data Index: 1443386 (Python Code)

Max Activating Token Index: 112

Text #2

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.8273. Min Act: -0.0002

Data Index: 1626402 (Python Code)

Max Activating Token Index: 218

Text #3

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.7882. Min Act: -0.0002

Data Index: 1483824 (Python Code)

Max Activating Token Index: 211

Text #4

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.6928. Min Act: -0.0002

Data Index: 1626010 (Python Code)

Max Activating Token Index: 184

Text #5

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.6281. Min Act: -0.0002

Data Index: 1613958 (Python Code)

Max Activating Token Index: 135

Text #6

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.6919. Min Act: -0.0002

Data Index: 1546622 (Python Code)

Max Activating Token Index: 126

Text #7

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.5713. Min Act: -0.0002

Data Index: 1540341 (Python Code)

Max Activating Token Index: 758

Text #8

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.6417. Min Act: -0.0002

Data Index: 1628321 (Python Code)

Max Activating Token Index: 89

Text #9

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.6608. Min Act: -0.0002

Data Index: 1449674 (Python Code)

Max Activating Token Index: 160

Text #10

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.5706. Min Act: -0.0002

Data Index: 1378832 (Python Code)

Max Activating Token Index: 306

Text #11

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.5300. Min Act: -0.0002

Data Index: 1558011 (Python Code)

Max Activating Token Index: 578

Text #12

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.5635. Min Act: -0.0002

Data Index: 1366950 (Python Code)

Max Activating Token Index: 67

Text #13

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.6366. Min Act: -0.0002

Data Index: 1480782 (Python Code)

Max Activating Token Index: 367

Text #14

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.6357. Min Act: -0.0002

Data Index: 1464302 (Python Code)

Max Activating Token Index: 238

Text #15

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.6440. Min Act: -0.0002

Data Index: 1378820 (Python Code)

Max Activating Token Index: 29

Text #16

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.5672. Min Act: -0.0002

Data Index: 1593919 (Python Code)

Max Activating Token Index: 148

Text #17

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.5709. Min Act: -0.0002

Data Index: 1537140 (Python Code)

Max Activating Token Index: 190

Text #18

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.6114. Min Act: -0.0002

Data Index: 1616893 (Python Code)

Max Activating Token Index: 40

Text #19

Max Range: 0.8273. Min Range: -0.8273

Max Act: 0.6513. Min Act: -0.0002

Data Index: 1493720 (Python Code)

Max Activating Token Index: 84