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

Dataset: The Pile

Neuron 2678 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.4636. Min Act: -0.0000

Data Index: 1654403 (The Pile)

Max Activating Token Index: 905

Text #1

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2447. Min Act: -0.0000

Data Index: 243097 (The Pile)

Max Activating Token Index: 266

Text #2

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1705568 (The Pile)

Max Activating Token Index: 803

Text #3

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2169. Min Act: -0.0000

Data Index: 1527969 (The Pile)

Max Activating Token Index: 452

Text #4

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1601. Min Act: -0.0000

Data Index: 1838604 (The Pile)

Max Activating Token Index: 341

Text #5

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2754. Min Act: -0.0000

Data Index: 814717 (The Pile)

Max Activating Token Index: 336

Text #6

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1007. Min Act: -0.0000

Data Index: 1251544 (The Pile)

Max Activating Token Index: 568

Text #7

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1520. Min Act: -0.0000

Data Index: 1583397 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1432. Min Act: -0.0000

Data Index: 1049765 (The Pile)

Max Activating Token Index: 293

Text #9

Max Range: 1.4636. Min Range: -1.4636

Max Act: 0.8224. Min Act: -0.0000

Data Index: 758513 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.0374. Min Act: -0.0000

Data Index: 276678 (The Pile)

Max Activating Token Index: 462

Text #11

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1095. Min Act: -0.0000

Data Index: 471157 (The Pile)

Max Activating Token Index: 335

Text #12

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1023. Min Act: -0.0000

Data Index: 1910748 (The Pile)

Max Activating Token Index: 628

Text #13

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.0412. Min Act: -0.0000

Data Index: 605834 (The Pile)

Max Activating Token Index: 674

Text #14

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1022. Min Act: -0.0000

Data Index: 87834 (The Pile)

Max Activating Token Index: 393

Text #15

Max Range: 1.4636. Min Range: -1.4636

Max Act: 0.9659. Min Act: -0.0000

Data Index: 990890 (The Pile)

Max Activating Token Index: 383

Text #16

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.0376. Min Act: -0.0000

Data Index: 1505248 (The Pile)

Max Activating Token Index: 208

Text #17

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.0034. Min Act: -0.0000

Data Index: 1992435 (The Pile)

Max Activating Token Index: 650

Text #18

Max Range: 1.4636. Min Range: -1.4636

Max Act: 0.9736. Min Act: -0.0000

Data Index: 1239707 (The Pile)

Max Activating Token Index: 729

Text #19

Max Range: 1.4636. Min Range: -1.4636

Max Act: 0.9432. Min Act: -0.0000

Data Index: 1131856 (The Pile)

Max Activating Token Index: 265