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

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

Neuron 4580 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.8155. Min Act: -0.0000

Data Index: 1288366 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.2392. Min Act: -0.0000

Data Index: 94616 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.3903. Min Act: -0.0000

Data Index: 481372 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.3716. Min Act: -0.0000

Data Index: 50031 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.3290. Min Act: -0.0000

Data Index: 551071 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.3307. Min Act: -0.0000

Data Index: 1123039 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.4722. Min Act: -0.0000

Data Index: 531565 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.3614. Min Act: -0.0000

Data Index: 1204081 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.2833. Min Act: -0.0000

Data Index: 438986 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.2679. Min Act: -0.0000

Data Index: 624836 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.1819. Min Act: -0.0000

Data Index: 1043921 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.2105. Min Act: -0.0000

Data Index: 889624 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.1999. Min Act: -0.0000

Data Index: 1281613 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.1860. Min Act: -0.0000

Data Index: 1232054 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.2582. Min Act: -0.0000

Data Index: 1112541 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.1741. Min Act: -0.0000

Data Index: 868395 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.1731. Min Act: -0.0000

Data Index: 1321379 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.1375. Min Act: -0.0000

Data Index: 1255495 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.0635. Min Act: -0.0000

Data Index: 41331 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 1.8155. Min Range: -1.8155

Max Act: 1.0466. Min Act: -0.0000

Data Index: 134970 (C4 (Web Text))

Max Activating Token Index: 459