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

Dataset: The Pile

Neuron 662 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1051121 (The Pile)

Max Activating Token Index: 990

Text #1

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1638. Min Act: -0.0000

Data Index: 1924093 (The Pile)

Max Activating Token Index: 404

Text #2

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1683. Min Act: -0.0000

Data Index: 897947 (The Pile)

Max Activating Token Index: 377

Text #3

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1742. Min Act: -0.0000

Data Index: 632013 (The Pile)

Max Activating Token Index: 826

Text #4

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1588. Min Act: -0.0000

Data Index: 1268287 (The Pile)

Max Activating Token Index: 441

Text #5

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1589. Min Act: -0.0000

Data Index: 304780 (The Pile)

Max Activating Token Index: 272

Text #6

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1627. Min Act: -0.0000

Data Index: 945344 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1624. Min Act: -0.0000

Data Index: 1298601 (The Pile)

Max Activating Token Index: 477

Text #8

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1560. Min Act: -0.0000

Data Index: 570504 (The Pile)

Max Activating Token Index: 221

Text #9

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1597. Min Act: -0.0000

Data Index: 1276881 (The Pile)

Max Activating Token Index: 908

Text #10

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1556. Min Act: -0.0000

Data Index: 323957 (The Pile)

Max Activating Token Index: 352

Text #11

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1487567 (The Pile)

Max Activating Token Index: 698

Text #12

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1492. Min Act: -0.0000

Data Index: 515304 (The Pile)

Max Activating Token Index: 723

Text #13

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1542. Min Act: -0.0000

Data Index: 393812 (The Pile)

Max Activating Token Index: 65

Text #14

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1511. Min Act: -0.0000

Data Index: 439907 (The Pile)

Max Activating Token Index: 695

Text #15

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1540356 (The Pile)

Max Activating Token Index: 149

Text #16

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1674685 (The Pile)

Max Activating Token Index: 952

Text #17

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1331. Min Act: -0.0000

Data Index: 26488 (The Pile)

Max Activating Token Index: 989

Text #18

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1451706 (The Pile)

Max Activating Token Index: 607

Text #19

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1270. Min Act: -0.0000

Data Index: 1337144 (The Pile)

Max Activating Token Index: 927