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

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

Neuron 1009 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0840. Min Act: -0.0000

Data Index: 1397470 (Python Code)

Max Activating Token Index: 938

Text #1

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0723. Min Act: -0.0000

Data Index: 578652 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0604. Min Act: -0.0000

Data Index: 1325137 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0562. Min Act: -0.0000

Data Index: 1174851 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0603. Min Act: -0.0000

Data Index: 995061 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0571. Min Act: -0.0000

Data Index: 1100415 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0570. Min Act: -0.0000

Data Index: 224932 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0596. Min Act: -0.0000

Data Index: 963109 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0546. Min Act: -0.0000

Data Index: 1238164 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0526. Min Act: -0.0000

Data Index: 940707 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0495. Min Act: -0.0000

Data Index: 31997 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0558. Min Act: -0.0000

Data Index: 537908 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0474. Min Act: -0.0000

Data Index: 1207341 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0497. Min Act: -0.0000

Data Index: 768744 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0557. Min Act: -0.0000

Data Index: 918921 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0467. Min Act: -0.0000

Data Index: 554999 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0479. Min Act: -0.0000

Data Index: 1186219 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0508. Min Act: -0.0000

Data Index: 1468191 (Python Code)

Max Activating Token Index: 979

Text #18

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0452. Min Act: -0.0000

Data Index: 867192 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0467. Min Act: -0.0000

Data Index: 842554 (C4 (Web Text))

Max Activating Token Index: 901