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

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

Neuron 3822 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: 0.7500. Min Range: -0.7500

Max Act: 0.7500. Min Act: -0.0000

Data Index: 1465569 (Python Code)

Max Activating Token Index: 553

Text #1

Max Range: 0.7500. Min Range: -0.7500

Max Act: 0.7339. Min Act: -0.0000

Data Index: 1499220 (Python Code)

Max Activating Token Index: 250

Text #2

Max Range: 0.7500. Min Range: -0.7500

Max Act: 0.7062. Min Act: -0.0000

Data Index: 1504532 (Python Code)

Max Activating Token Index: 882

Text #3

Max Range: 0.7500. Min Range: -0.7500

Max Act: 0.6953. Min Act: -0.0000

Data Index: 1489919 (Python Code)

Max Activating Token Index: 933

Text #4

Max Range: 0.7500. Min Range: -0.7500

Max Act: 0.6599. Min Act: -0.0000

Data Index: 1284896 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.7500. Min Range: -0.7500

Max Act: 0.7010. Min Act: -0.0000

Data Index: 933247 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.7500. Min Range: -0.7500

Max Act: 0.6704. Min Act: -0.0000

Data Index: 1384809 (Python Code)

Max Activating Token Index: 717

Text #7

Max Range: 0.7500. Min Range: -0.7500

Max Act: 0.6857. Min Act: -0.0000

Data Index: 1495742 (Python Code)

Max Activating Token Index: 85

Text #8

Max Range: 0.7500. Min Range: -0.7500

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1419765 (Python Code)

Max Activating Token Index: 992

Text #9

Max Range: 0.7500. Min Range: -0.7500

Max Act: 0.6760. Min Act: -0.0000

Data Index: 389976 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 0.7500. Min Range: -0.7500

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1471471 (Python Code)

Max Activating Token Index: 217

Text #11

Max Range: 0.7500. Min Range: -0.7500

Max Act: 0.6648. Min Act: -0.0000

Data Index: 299303 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.7500. Min Range: -0.7500

Max Act: 0.6640. Min Act: -0.0000

Data Index: 191633 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.7500. Min Range: -0.7500

Max Act: 0.6390. Min Act: -0.0000

Data Index: 462978 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.7500. Min Range: -0.7500

Max Act: 0.6287. Min Act: -0.0000

Data Index: 995042 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.7500. Min Range: -0.7500

Max Act: 0.6747. Min Act: -0.0000

Data Index: 285319 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.7500. Min Range: -0.7500

Max Act: 0.6488. Min Act: -0.0000

Data Index: 662069 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.7500. Min Range: -0.7500

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1376586 (Python Code)

Max Activating Token Index: 974

Text #18

Max Range: 0.7500. Min Range: -0.7500

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1390756 (Python Code)

Max Activating Token Index: 887

Text #19

Max Range: 0.7500. Min Range: -0.7500

Max Act: 0.6400. Min Act: -0.0000

Data Index: 694457 (C4 (Web Text))

Max Activating Token Index: 418