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

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

Neuron 3685 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.8731. Min Act: 0.0000

Data Index: 1388774 (Python Code)

Max Activating Token Index: 468

Text #1

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1649182 (Python Code)

Max Activating Token Index: 875

Text #2

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6996. Min Act: -0.0000

Data Index: 1499713 (Python Code)

Max Activating Token Index: 731

Text #3

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6823. Min Act: -0.0000

Data Index: 1545094 (Python Code)

Max Activating Token Index: 565

Text #4

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6568. Min Act: 0.0001

Data Index: 1376349 (Python Code)

Max Activating Token Index: 382

Text #5

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1442179 (Python Code)

Max Activating Token Index: 741

Text #6

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.5936. Min Act: -0.0000

Data Index: 1486106 (Python Code)

Max Activating Token Index: 721

Text #7

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.6110. Min Act: -0.0000

Data Index: 1637866 (Python Code)

Max Activating Token Index: 695

Text #8

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.5696. Min Act: -0.0000

Data Index: 1610003 (Python Code)

Max Activating Token Index: 349

Text #9

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1444314 (Python Code)

Max Activating Token Index: 821

Text #10

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.5525. Min Act: -0.0000

Data Index: 581763 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1519163 (Python Code)

Max Activating Token Index: 844

Text #12

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.5643. Min Act: 0.0001

Data Index: 1474030 (Python Code)

Max Activating Token Index: 678

Text #13

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.5124. Min Act: -0.0000

Data Index: 87697 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1071390 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.5178. Min Act: -0.0000

Data Index: 1363242 (Python Code)

Max Activating Token Index: 307

Text #16

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.4870. Min Act: 0.0000

Data Index: 1566933 (Python Code)

Max Activating Token Index: 928

Text #17

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.5232. Min Act: -0.0000

Data Index: 775311 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1580283 (Python Code)

Max Activating Token Index: 154

Text #19

Max Range: 0.8794. Min Range: -0.8794

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1527899 (Python Code)

Max Activating Token Index: 259