Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1428 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1177653 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0580. Min Act: -0.0002

Data Index: 747009 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0488. Min Act: -0.0003

Data Index: 557793 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0474. Min Act: -0.0004

Data Index: 87898 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0476. Min Act: -0.0003

Data Index: 727396 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0477. Min Act: -0.0003

Data Index: 51994 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0453. Min Act: -0.0003

Data Index: 123582 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0456. Min Act: -0.0003

Data Index: 369699 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1159784 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1174445 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1083329 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0452. Min Act: -0.0002

Data Index: 213132 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1096498 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0462. Min Act: -0.0002

Data Index: 518738 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0440. Min Act: -0.0003

Data Index: 444781 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0453. Min Act: -0.0004

Data Index: 826360 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0450. Min Act: -0.0003

Data Index: 159267 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0439. Min Act: -0.0003

Data Index: 194684 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0444. Min Act: -0.0003

Data Index: 699804 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0439. Min Act: -0.0003

Data Index: 1109655 (C4 (Web Text))

Max Activating Token Index: 236