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

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

Neuron 1000 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0817. Min Act: -0.0000

Data Index: 1074787 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0826. Min Act: -0.0000

Data Index: 86375 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1011778 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0680. Min Act: -0.0000

Data Index: 254784 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0672. Min Act: -0.0000

Data Index: 609112 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0616. Min Act: -0.0000

Data Index: 91738 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0631. Min Act: -0.0001

Data Index: 868565 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0572. Min Act: -0.0000

Data Index: 6640 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0586. Min Act: -0.0000

Data Index: 396510 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0577. Min Act: -0.0000

Data Index: 952010 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0567. Min Act: -0.0000

Data Index: 101899 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0614. Min Act: -0.0000

Data Index: 803636 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0578. Min Act: -0.0000

Data Index: 1043513 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0619. Min Act: -0.0000

Data Index: 382409 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0474. Min Act: -0.0000

Data Index: 226797 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0516. Min Act: -0.0000

Data Index: 106970 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0501. Min Act: -0.0000

Data Index: 220806 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0512. Min Act: -0.0000

Data Index: 8498 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0499. Min Act: -0.0000

Data Index: 607212 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0456. Min Act: -0.0000

Data Index: 1129678 (C4 (Web Text))

Max Activating Token Index: 553