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

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

Neuron 2398 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.4311. Min Act: -0.0002

Data Index: 954382 (C4 (Web Text))

Max Activating Token Index: 534

Text #1

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.4268. Min Act: -0.0002

Data Index: 586660 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.3914. Min Act: -0.0002

Data Index: 882025 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.3537. Min Act: -0.0002

Data Index: 659040 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.3269. Min Act: -0.0002

Data Index: 673766 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.3196. Min Act: -0.0002

Data Index: 1279037 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.4079. Min Act: -0.0002

Data Index: 701171 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.3795. Min Act: -0.0002

Data Index: 782574 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.3610. Min Act: -0.0002

Data Index: 942159 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.3472. Min Act: -0.0002

Data Index: 1235339 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.3630. Min Act: -0.0002

Data Index: 1056921 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.3860. Min Act: -0.0002

Data Index: 860826 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.4063. Min Act: -0.0002

Data Index: 664690 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.3602. Min Act: -0.0002

Data Index: 419797 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.3437. Min Act: -0.0002

Data Index: 214967 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.3783. Min Act: -0.0002

Data Index: 667506 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.3378. Min Act: -0.0002

Data Index: 390369 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.3573. Min Act: -0.0002

Data Index: 329236 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.3465. Min Act: -0.0002

Data Index: 234361 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 0.4311. Min Range: -0.4311

Max Act: 0.3341. Min Act: -0.0002

Data Index: 553606 (C4 (Web Text))

Max Activating Token Index: 302