Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1355 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1508. Min Range: -1.1508

Max Act: 1.1508. Min Act: -0.0001

Data Index: 1540727 (Python Code)

Max Activating Token Index: 384

Text #1

Max Range: 1.1508. Min Range: -1.1508

Max Act: 1.1368. Min Act: -0.0001

Data Index: 1413142 (Python Code)

Max Activating Token Index: 157

Text #2

Max Range: 1.1508. Min Range: -1.1508

Max Act: 1.0727. Min Act: -0.0001

Data Index: 1480586 (Python Code)

Max Activating Token Index: 796

Text #3

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.9390. Min Act: -0.0001

Data Index: 1367412 (Python Code)

Max Activating Token Index: 173

Text #4

Max Range: 1.1508. Min Range: -1.1508

Max Act: 1.0221. Min Act: -0.0001

Data Index: 1498626 (Python Code)

Max Activating Token Index: 668

Text #5

Max Range: 1.1508. Min Range: -1.1508

Max Act: 1.0493. Min Act: -0.0001

Data Index: 1421813 (Python Code)

Max Activating Token Index: 254

Text #6

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.9713. Min Act: -0.0001

Data Index: 1375219 (Python Code)

Max Activating Token Index: 241

Text #7

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.9197. Min Act: -0.0001

Data Index: 1435400 (Python Code)

Max Activating Token Index: 443

Text #8

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.8816. Min Act: -0.0001

Data Index: 1553887 (Python Code)

Max Activating Token Index: 737

Text #9

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.8514. Min Act: -0.0001

Data Index: 1644293 (Python Code)

Max Activating Token Index: 775

Text #10

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.8856. Min Act: -0.0001

Data Index: 1565306 (Python Code)

Max Activating Token Index: 156

Text #11

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.8850. Min Act: -0.0001

Data Index: 1474471 (Python Code)

Max Activating Token Index: 851

Text #12

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.8783. Min Act: -0.0001

Data Index: 1366949 (Python Code)

Max Activating Token Index: 461

Text #13

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.8451. Min Act: -0.0001

Data Index: 1499069 (Python Code)

Max Activating Token Index: 149

Text #14

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.9194. Min Act: -0.0001

Data Index: 1435451 (Python Code)

Max Activating Token Index: 878

Text #15

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.8823. Min Act: -0.0001

Data Index: 1599042 (Python Code)

Max Activating Token Index: 163

Text #16

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.8660. Min Act: -0.0001

Data Index: 1432677 (Python Code)

Max Activating Token Index: 273

Text #17

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.8218. Min Act: -0.0001

Data Index: 1641657 (Python Code)

Max Activating Token Index: 618

Text #18

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.8248. Min Act: -0.0001

Data Index: 1467359 (Python Code)

Max Activating Token Index: 301

Text #19

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.7931. Min Act: -0.0001

Data Index: 1454360 (Python Code)

Max Activating Token Index: 275