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

Dataset: The Pile

Neuron 4905 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1519. Min Range: -1.1519

Max Act: 1.1519. Min Act: -0.0000

Data Index: 862194 (The Pile)

Max Activating Token Index: 377

Text #1

Max Range: 1.1519. Min Range: -1.1519

Max Act: 1.1198. Min Act: -0.0000

Data Index: 1571652 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 1.1519. Min Range: -1.1519

Max Act: 1.1420. Min Act: -0.0000

Data Index: 429122 (The Pile)

Max Activating Token Index: 19

Text #3

Max Range: 1.1519. Min Range: -1.1519

Max Act: 1.0804. Min Act: -0.0000

Data Index: 707621 (The Pile)

Max Activating Token Index: 170

Text #4

Max Range: 1.1519. Min Range: -1.1519

Max Act: 1.0375. Min Act: -0.0000

Data Index: 1021382 (The Pile)

Max Activating Token Index: 5

Text #5

Max Range: 1.1519. Min Range: -1.1519

Max Act: 1.0441. Min Act: -0.0000

Data Index: 1176980 (The Pile)

Max Activating Token Index: 24

Text #6

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1867922 (The Pile)

Max Activating Token Index: 8

Text #7

Max Range: 1.1519. Min Range: -1.1519

Max Act: 1.0630. Min Act: -0.0000

Data Index: 587467 (The Pile)

Max Activating Token Index: 475

Text #8

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.9720. Min Act: -0.0000

Data Index: 694394 (The Pile)

Max Activating Token Index: 411

Text #9

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.9596. Min Act: -0.0000

Data Index: 1612044 (The Pile)

Max Activating Token Index: 632

Text #10

Max Range: 1.1519. Min Range: -1.1519

Max Act: 1.0146. Min Act: -0.0000

Data Index: 158301 (The Pile)

Max Activating Token Index: 315

Text #11

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.9639. Min Act: -0.0000

Data Index: 838419 (The Pile)

Max Activating Token Index: 825

Text #12

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.9645. Min Act: -0.0000

Data Index: 1431414 (The Pile)

Max Activating Token Index: 24

Text #13

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.9650. Min Act: -0.0000

Data Index: 339089 (The Pile)

Max Activating Token Index: 707

Text #14

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.9939. Min Act: -0.0000

Data Index: 1675925 (The Pile)

Max Activating Token Index: 176

Text #15

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.9486. Min Act: -0.0000

Data Index: 1687442 (The Pile)

Max Activating Token Index: 542

Text #16

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.9393. Min Act: -0.0000

Data Index: 506896 (The Pile)

Max Activating Token Index: 15

Text #17

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.9774. Min Act: -0.0000

Data Index: 1560034 (The Pile)

Max Activating Token Index: 189

Text #18

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.8768. Min Act: -0.0000

Data Index: 1927409 (The Pile)

Max Activating Token Index: 821

Text #19

Max Range: 1.1519. Min Range: -1.1519

Max Act: 0.8595. Min Act: -0.0000

Data Index: 1651705 (The Pile)

Max Activating Token Index: 982