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

Dataset: The Pile

Neuron 2482 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.2809. Min Act: -0.0000

Data Index: 1815887 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.3462. Min Act: -0.0000

Data Index: 942039 (The Pile)

Max Activating Token Index: 269

Text #2

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.1273. Min Act: -0.0000

Data Index: 1236411 (The Pile)

Max Activating Token Index: 952

Text #3

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.1852. Min Act: -0.0000

Data Index: 1816251 (The Pile)

Max Activating Token Index: 472

Text #4

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.0861. Min Act: -0.0000

Data Index: 194188 (The Pile)

Max Activating Token Index: 143

Text #5

Max Range: 1.3462. Min Range: -1.3462

Max Act: 0.9809. Min Act: -0.0000

Data Index: 721730 (The Pile)

Max Activating Token Index: 627

Text #6

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1820903 (The Pile)

Max Activating Token Index: 786

Text #7

Max Range: 1.3462. Min Range: -1.3462

Max Act: 0.9658. Min Act: -0.0000

Data Index: 215623 (The Pile)

Max Activating Token Index: 461

Text #8

Max Range: 1.3462. Min Range: -1.3462

Max Act: 0.9318. Min Act: -0.0000

Data Index: 472892 (The Pile)

Max Activating Token Index: 719

Text #9

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.0484. Min Act: -0.0000

Data Index: 751073 (The Pile)

Max Activating Token Index: 408

Text #10

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.0073. Min Act: -0.0000

Data Index: 668110 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 1.3462. Min Range: -1.3462

Max Act: 0.9737. Min Act: -0.0000

Data Index: 183468 (The Pile)

Max Activating Token Index: 524

Text #12

Max Range: 1.3462. Min Range: -1.3462

Max Act: 0.9979. Min Act: -0.0000

Data Index: 561700 (The Pile)

Max Activating Token Index: 384

Text #13

Max Range: 1.3462. Min Range: -1.3462

Max Act: 0.9891. Min Act: -0.0000

Data Index: 1936421 (The Pile)

Max Activating Token Index: 67

Text #14

Max Range: 1.3462. Min Range: -1.3462

Max Act: 0.9863. Min Act: -0.0000

Data Index: 228608 (The Pile)

Max Activating Token Index: 271

Text #15

Max Range: 1.3462. Min Range: -1.3462

Max Act: 0.9492. Min Act: -0.0000

Data Index: 1415625 (The Pile)

Max Activating Token Index: 106

Text #16

Max Range: 1.3462. Min Range: -1.3462

Max Act: 0.9153. Min Act: -0.0000

Data Index: 1124652 (The Pile)

Max Activating Token Index: 114

Text #17

Max Range: 1.3462. Min Range: -1.3462

Max Act: 0.9395. Min Act: -0.0000

Data Index: 1451953 (The Pile)

Max Activating Token Index: 1006

Text #18

Max Range: 1.3462. Min Range: -1.3462

Max Act: 0.8831. Min Act: -0.0000

Data Index: 1476524 (The Pile)

Max Activating Token Index: 605

Text #19

Max Range: 1.3462. Min Range: -1.3462

Max Act: 0.9353. Min Act: -0.0000

Data Index: 444165 (The Pile)

Max Activating Token Index: 212