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

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

Neuron 891 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: 0.0877. Min Range: -0.0877

Max Act: 0.0877. Min Act: -0.0000

Data Index: 413833 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0837. Min Act: -0.0000

Data Index: 1211112 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1136270 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0754. Min Act: -0.0000

Data Index: 171841 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0794. Min Act: -0.0000

Data Index: 435707 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0713. Min Act: -0.0000

Data Index: 660085 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0696. Min Act: -0.0000

Data Index: 903246 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0709. Min Act: -0.0000

Data Index: 1351734 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0706. Min Act: -0.0000

Data Index: 1282662 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0684. Min Act: -0.0000

Data Index: 127821 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0702. Min Act: -0.0000

Data Index: 938016 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0704. Min Act: -0.0000

Data Index: 82326 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0703. Min Act: -0.0000

Data Index: 486508 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0661. Min Act: -0.0000

Data Index: 945230 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0678. Min Act: -0.0000

Data Index: 1250967 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0642. Min Act: -0.0000

Data Index: 330496 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0636. Min Act: -0.0000

Data Index: 764502 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0626. Min Act: -0.0000

Data Index: 1317989 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0608. Min Act: -0.0000

Data Index: 241421 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0616. Min Act: -0.0000

Data Index: 698050 (C4 (Web Text))

Max Activating Token Index: 942