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

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

Neuron 4696 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: 1.1759. Min Range: -1.1759

Max Act: 1.1759. Min Act: -0.0000

Data Index: 312846 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.9732. Min Act: -0.0000

Data Index: 769214 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.9473. Min Act: -0.0000

Data Index: 1237394 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.9450. Min Act: -0.0000

Data Index: 1191313 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.9102. Min Act: -0.0000

Data Index: 543409 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.9553. Min Act: -0.0000

Data Index: 1303281 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.8618. Min Act: -0.0000

Data Index: 294891 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1053971 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.8431. Min Act: -0.0000

Data Index: 950214 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.7938. Min Act: -0.0000

Data Index: 1097554 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.7696. Min Act: -0.0000

Data Index: 451454 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.7214. Min Act: -0.0000

Data Index: 190570 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1046434 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.7676. Min Act: -0.0000

Data Index: 69978 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.7075. Min Act: -0.0000

Data Index: 10361 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.7481. Min Act: -0.0000

Data Index: 442918 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.7274. Min Act: -0.0000

Data Index: 946096 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.7278. Min Act: -0.0000

Data Index: 439890 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.7768. Min Act: -0.0000

Data Index: 492225 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.7665. Min Act: -0.0000

Data Index: 809336 (C4 (Web Text))

Max Activating Token Index: 164