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

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

Neuron 4495 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: 0.0868. Min Range: -0.0868

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1303307 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0868. Min Act: -0.0002

Data Index: 619525 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1167518 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0821. Min Act: -0.0002

Data Index: 494404 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0778. Min Act: -0.0002

Data Index: 775447 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1001713 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0756. Min Act: -0.0002

Data Index: 357744 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0813. Min Act: -0.0002

Data Index: 68813 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0754. Min Act: -0.0002

Data Index: 206661 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0808. Min Act: -0.0002

Data Index: 205302 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0728. Min Act: -0.0002

Data Index: 478943 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0750. Min Act: -0.0002

Data Index: 864118 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0769. Min Act: -0.0002

Data Index: 954093 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0818. Min Act: -0.0002

Data Index: 684928 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0765. Min Act: -0.0002

Data Index: 881104 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0764. Min Act: -0.0002

Data Index: 614037 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0761. Min Act: -0.0002

Data Index: 227390 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1220753 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0668. Min Act: -0.0002

Data Index: 449681 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0798. Min Act: -0.0002

Data Index: 234123 (C4 (Web Text))

Max Activating Token Index: 845