Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1240 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1109828 (The Pile)

Max Activating Token Index: 712

Text #1

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1793. Min Act: -0.0000

Data Index: 618234 (The Pile)

Max Activating Token Index: 914

Text #2

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1908. Min Act: -0.0000

Data Index: 850360 (The Pile)

Max Activating Token Index: 426

Text #3

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1892. Min Act: -0.0000

Data Index: 208679 (The Pile)

Max Activating Token Index: 371

Text #4

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1685. Min Act: -0.0000

Data Index: 866643 (The Pile)

Max Activating Token Index: 353

Text #5

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1729. Min Act: -0.0000

Data Index: 396553 (The Pile)

Max Activating Token Index: 230

Text #6

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1764. Min Act: -0.0000

Data Index: 1122010 (The Pile)

Max Activating Token Index: 950

Text #7

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1627. Min Act: -0.0000

Data Index: 371581 (The Pile)

Max Activating Token Index: 673

Text #8

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1588. Min Act: -0.0000

Data Index: 1802315 (The Pile)

Max Activating Token Index: 806

Text #9

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1509. Min Act: -0.0000

Data Index: 369208 (The Pile)

Max Activating Token Index: 495

Text #10

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1570. Min Act: -0.0000

Data Index: 1415066 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1612. Min Act: -0.0000

Data Index: 506959 (The Pile)

Max Activating Token Index: 667

Text #12

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1988485 (The Pile)

Max Activating Token Index: 713

Text #13

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1539. Min Act: -0.0000

Data Index: 1468648 (The Pile)

Max Activating Token Index: 689

Text #14

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1527. Min Act: -0.0000

Data Index: 1614882 (The Pile)

Max Activating Token Index: 422

Text #15

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1610. Min Act: -0.0000

Data Index: 1528029 (The Pile)

Max Activating Token Index: 697

Text #16

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1645. Min Act: -0.0000

Data Index: 248433 (The Pile)

Max Activating Token Index: 249

Text #17

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1476. Min Act: -0.0000

Data Index: 733051 (The Pile)

Max Activating Token Index: 819

Text #18

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1673. Min Act: -0.0000

Data Index: 1323389 (The Pile)

Max Activating Token Index: 253

Text #19

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1601. Min Act: -0.0000

Data Index: 1483577 (The Pile)

Max Activating Token Index: 195