Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 24 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.2717. Min Act: -0.0003

Data Index: 119321 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.2277. Min Act: -0.0002

Data Index: 57281 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.1852. Min Act: -0.0002

Data Index: 1325750 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.1852. Min Act: -0.0003

Data Index: 1241710 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.1670. Min Act: -0.0002

Data Index: 345660 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.1366. Min Act: -0.0002

Data Index: 835692 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.1027. Min Act: -0.0002

Data Index: 209858 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0505. Min Act: -0.0002

Data Index: 1209037 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0755. Min Act: -0.0002

Data Index: 1266718 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0800. Min Act: -0.0002

Data Index: 1147683 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0759. Min Act: -0.0002

Data Index: 252795 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0508. Min Act: -0.0002

Data Index: 212322 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0308. Min Act: -0.0002

Data Index: 363091 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0676. Min Act: -0.0003

Data Index: 382844 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0252. Min Act: -0.0002

Data Index: 306941 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0421. Min Act: -0.0002

Data Index: 127131 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0789. Min Act: -0.0002

Data Index: 532417 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0447. Min Act: -0.0002

Data Index: 353678 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0300. Min Act: -0.0002

Data Index: 184787 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 1.2717. Min Range: -1.2717

Max Act: 1.0160. Min Act: -0.0002

Data Index: 229268 (C4 (Web Text))

Max Activating Token Index: 16