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

Dataset: The Pile

Neuron 372 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: 3.4800. Min Range: -3.4800

Max Act: 3.4800. Min Act: -0.0000

Data Index: 150963 (The Pile)

Max Activating Token Index: 762

Text #1

Max Range: 3.4800. Min Range: -3.4800

Max Act: 2.4691. Min Act: -0.0000

Data Index: 1213865 (The Pile)

Max Activating Token Index: 969

Text #2

Max Range: 3.4800. Min Range: -3.4800

Max Act: 2.3683. Min Act: -0.0000

Data Index: 830714 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 3.4800. Min Range: -3.4800

Max Act: 2.0694. Min Act: -0.0000

Data Index: 319006 (The Pile)

Max Activating Token Index: 373

Text #4

Max Range: 3.4800. Min Range: -3.4800

Max Act: 1.9772. Min Act: -0.0000

Data Index: 1919733 (The Pile)

Max Activating Token Index: 466

Text #5

Max Range: 3.4800. Min Range: -3.4800

Max Act: 2.4138. Min Act: -0.0000

Data Index: 1165377 (The Pile)

Max Activating Token Index: 92

Text #6

Max Range: 3.4800. Min Range: -3.4800

Max Act: 1.9421. Min Act: -0.0000

Data Index: 481299 (The Pile)

Max Activating Token Index: 922

Text #7

Max Range: 3.4800. Min Range: -3.4800

Max Act: 1.9876. Min Act: -0.0000

Data Index: 148057 (The Pile)

Max Activating Token Index: 747

Text #8

Max Range: 3.4800. Min Range: -3.4800

Max Act: 1.9845. Min Act: -0.0000

Data Index: 1635824 (The Pile)

Max Activating Token Index: 140

Text #9

Max Range: 3.4800. Min Range: -3.4800

Max Act: 1.9758. Min Act: -0.0000

Data Index: 1131826 (The Pile)

Max Activating Token Index: 665

Text #10

Max Range: 3.4800. Min Range: -3.4800

Max Act: 1.9386. Min Act: -0.0000

Data Index: 1801589 (The Pile)

Max Activating Token Index: 496

Text #11

Max Range: 3.4800. Min Range: -3.4800

Max Act: 2.0401. Min Act: -0.0000

Data Index: 1390949 (The Pile)

Max Activating Token Index: 133

Text #12

Max Range: 3.4800. Min Range: -3.4800

Max Act: 1.9997. Min Act: -0.0000

Data Index: 1074938 (The Pile)

Max Activating Token Index: 964

Text #13

Max Range: 3.4800. Min Range: -3.4800

Max Act: 1.9155. Min Act: -0.0000

Data Index: 1731344 (The Pile)

Max Activating Token Index: 245

Text #14

Max Range: 3.4800. Min Range: -3.4800

Max Act: 1.9286. Min Act: -0.0000

Data Index: 539384 (The Pile)

Max Activating Token Index: 582

Text #15

Max Range: 3.4800. Min Range: -3.4800

Max Act: 1.8140. Min Act: -0.0000

Data Index: 294892 (The Pile)

Max Activating Token Index: 831

Text #16

Max Range: 3.4800. Min Range: -3.4800

Max Act: 1.8017. Min Act: -0.0000

Data Index: 1696840 (The Pile)

Max Activating Token Index: 685

Text #17

Max Range: 3.4800. Min Range: -3.4800

Max Act: 1.8826. Min Act: -0.0000

Data Index: 1823755 (The Pile)

Max Activating Token Index: 567

Text #18

Max Range: 3.4800. Min Range: -3.4800

Max Act: 2.0997. Min Act: -0.0000

Data Index: 1328682 (The Pile)

Max Activating Token Index: 319

Text #19

Max Range: 3.4800. Min Range: -3.4800

Max Act: 2.1718. Min Act: -0.0000

Data Index: 496309 (The Pile)

Max Activating Token Index: 978