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

Dataset: The Pile

Neuron 1518 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: 1.2286. Min Range: -1.2286

Max Act: 1.2286. Min Act: -0.0000

Data Index: 495841 (The Pile)

Max Activating Token Index: 48

Text #1

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.9809. Min Act: -0.0000

Data Index: 123557 (The Pile)

Max Activating Token Index: 606

Text #2

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.8965. Min Act: -0.0000

Data Index: 1097264 (The Pile)

Max Activating Token Index: 227

Text #3

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.8572. Min Act: -0.0000

Data Index: 820716 (The Pile)

Max Activating Token Index: 851

Text #4

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.8646. Min Act: -0.0000

Data Index: 1259589 (The Pile)

Max Activating Token Index: 463

Text #5

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.7678. Min Act: -0.0000

Data Index: 158075 (The Pile)

Max Activating Token Index: 124

Text #6

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1223461 (The Pile)

Max Activating Token Index: 495

Text #7

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.7438. Min Act: -0.0000

Data Index: 1167640 (The Pile)

Max Activating Token Index: 469

Text #8

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.7113. Min Act: -0.0000

Data Index: 1548970 (The Pile)

Max Activating Token Index: 632

Text #9

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.7501. Min Act: -0.0000

Data Index: 935709 (The Pile)

Max Activating Token Index: 751

Text #10

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.7671. Min Act: -0.0000

Data Index: 523010 (The Pile)

Max Activating Token Index: 179

Text #11

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.6951. Min Act: -0.0000

Data Index: 1981884 (The Pile)

Max Activating Token Index: 942

Text #12

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.7557. Min Act: -0.0000

Data Index: 891009 (The Pile)

Max Activating Token Index: 560

Text #13

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.7216. Min Act: -0.0000

Data Index: 946891 (The Pile)

Max Activating Token Index: 122

Text #14

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1659311 (The Pile)

Max Activating Token Index: 363

Text #15

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.6588. Min Act: -0.0000

Data Index: 39768 (The Pile)

Max Activating Token Index: 871

Text #16

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1917714 (The Pile)

Max Activating Token Index: 296

Text #17

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1952635 (The Pile)

Max Activating Token Index: 350

Text #18

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.6544. Min Act: -0.0000

Data Index: 770336 (The Pile)

Max Activating Token Index: 755

Text #19

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1857501 (The Pile)

Max Activating Token Index: 405