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

Dataset: The Pile

Neuron 3934 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.3702. Min Act: -0.0000

Data Index: 1539667 (The Pile)

Max Activating Token Index: 502

Text #1

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.3230. Min Act: -0.0000

Data Index: 471693 (The Pile)

Max Activating Token Index: 905

Text #2

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.2845. Min Act: -0.0000

Data Index: 1013532 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.3323. Min Act: -0.0000

Data Index: 1722621 (The Pile)

Max Activating Token Index: 866

Text #4

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.2325. Min Act: -0.0000

Data Index: 97375 (The Pile)

Max Activating Token Index: 492

Text #5

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.0689. Min Act: -0.0000

Data Index: 1754627 (The Pile)

Max Activating Token Index: 641

Text #6

Max Range: 3.3702. Min Range: -3.3702

Max Act: 2.9179. Min Act: -0.0000

Data Index: 1472276 (The Pile)

Max Activating Token Index: 364

Text #7

Max Range: 3.3702. Min Range: -3.3702

Max Act: 2.7004. Min Act: -0.0000

Data Index: 480687 (The Pile)

Max Activating Token Index: 869

Text #8

Max Range: 3.3702. Min Range: -3.3702

Max Act: 2.9427. Min Act: -0.0000

Data Index: 154176 (The Pile)

Max Activating Token Index: 167

Text #9

Max Range: 3.3702. Min Range: -3.3702

Max Act: 2.6438. Min Act: -0.0000

Data Index: 924850 (The Pile)

Max Activating Token Index: 173

Text #10

Max Range: 3.3702. Min Range: -3.3702

Max Act: 3.1170. Min Act: -0.0000

Data Index: 1070727 (The Pile)

Max Activating Token Index: 603

Text #11

Max Range: 3.3702. Min Range: -3.3702

Max Act: 2.6235. Min Act: -0.0000

Data Index: 484585 (The Pile)

Max Activating Token Index: 570

Text #12

Max Range: 3.3702. Min Range: -3.3702

Max Act: 2.6539. Min Act: -0.0000

Data Index: 752104 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 3.3702. Min Range: -3.3702

Max Act: 2.7579. Min Act: -0.0000

Data Index: 1405573 (The Pile)

Max Activating Token Index: 738

Text #14

Max Range: 3.3702. Min Range: -3.3702

Max Act: 2.6253. Min Act: -0.0000

Data Index: 1746519 (The Pile)

Max Activating Token Index: 258

Text #15

Max Range: 3.3702. Min Range: -3.3702

Max Act: 2.8437. Min Act: -0.0000

Data Index: 1546491 (The Pile)

Max Activating Token Index: 385

Text #16

Max Range: 3.3702. Min Range: -3.3702

Max Act: 2.9523. Min Act: -0.0000

Data Index: 888803 (The Pile)

Max Activating Token Index: 516

Text #17

Max Range: 3.3702. Min Range: -3.3702

Max Act: 2.8024. Min Act: -0.0000

Data Index: 650706 (The Pile)

Max Activating Token Index: 439

Text #18

Max Range: 3.3702. Min Range: -3.3702

Max Act: 2.2980. Min Act: -0.0000

Data Index: 661949 (The Pile)

Max Activating Token Index: 752

Text #19

Max Range: 3.3702. Min Range: -3.3702

Max Act: 2.2308. Min Act: -0.0000

Data Index: 1621848 (The Pile)

Max Activating Token Index: 867