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

Dataset: The Pile

Neuron 2160 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: 1.8779. Min Range: -1.8779

Max Act: 1.8779. Min Act: -0.0000

Data Index: 69090 (The Pile)

Max Activating Token Index: 41

Text #1

Max Range: 1.8779. Min Range: -1.8779

Max Act: 1.7648. Min Act: -0.0000

Data Index: 1761078 (The Pile)

Max Activating Token Index: 931

Text #2

Max Range: 1.8779. Min Range: -1.8779

Max Act: 1.7328. Min Act: -0.0000

Data Index: 315926 (The Pile)

Max Activating Token Index: 493

Text #3

Max Range: 1.8779. Min Range: -1.8779

Max Act: 1.6703. Min Act: -0.0000

Data Index: 1004859 (The Pile)

Max Activating Token Index: 631

Text #4

Max Range: 1.8779. Min Range: -1.8779

Max Act: 1.8552. Min Act: -0.0000

Data Index: 1318954 (The Pile)

Max Activating Token Index: 630

Text #5

Max Range: 1.8779. Min Range: -1.8779

Max Act: 1.6569. Min Act: -0.0000

Data Index: 1793092 (The Pile)

Max Activating Token Index: 128

Text #6

Max Range: 1.8779. Min Range: -1.8779

Max Act: 1.6404. Min Act: -0.0000

Data Index: 97644 (The Pile)

Max Activating Token Index: 358

Text #7

Max Range: 1.8779. Min Range: -1.8779

Max Act: 1.6300. Min Act: -0.0000

Data Index: 736670 (The Pile)

Max Activating Token Index: 11

Text #8

Max Range: 1.8779. Min Range: -1.8779

Max Act: 1.5926. Min Act: -0.0000

Data Index: 1116504 (The Pile)

Max Activating Token Index: 693

Text #9

Max Range: 1.8779. Min Range: -1.8779

Max Act: 1.5482. Min Act: -0.0000

Data Index: 1591057 (The Pile)

Max Activating Token Index: 284

Text #10

Max Range: 1.8779. Min Range: -1.8779

Max Act: 1.5000. Min Act: -0.0000

Data Index: 823926 (The Pile)

Max Activating Token Index: 481

Text #11

Max Range: 1.8779. Min Range: -1.8779

Max Act: 1.5767. Min Act: -0.0000

Data Index: 226958 (The Pile)

Max Activating Token Index: 645

Text #12

Max Range: 1.8779. Min Range: -1.8779

Max Act: 1.3121. Min Act: -0.0000

Data Index: 651138 (The Pile)

Max Activating Token Index: 562

Text #13

Max Range: 1.8779. Min Range: -1.8779

Max Act: 1.4311. Min Act: -0.0000

Data Index: 1965989 (The Pile)

Max Activating Token Index: 598

Text #14

Max Range: 1.8779. Min Range: -1.8779

Max Act: 1.4469. Min Act: -0.0000

Data Index: 1542352 (The Pile)

Max Activating Token Index: 122

Text #15

Max Range: 1.8779. Min Range: -1.8779

Max Act: 1.4113. Min Act: -0.0000

Data Index: 1922455 (The Pile)

Max Activating Token Index: 15

Text #16

Max Range: 1.8779. Min Range: -1.8779

Max Act: 1.5502. Min Act: -0.0000

Data Index: 1238445 (The Pile)

Max Activating Token Index: 606

Text #17

Max Range: 1.8779. Min Range: -1.8779

Max Act: 1.2702. Min Act: -0.0000

Data Index: 1272852 (The Pile)

Max Activating Token Index: 746

Text #18

Max Range: 1.8779. Min Range: -1.8779

Max Act: 1.4051. Min Act: -0.0000

Data Index: 972595 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 1.8779. Min Range: -1.8779

Max Act: 1.2428. Min Act: -0.0000

Data Index: 1817279 (The Pile)

Max Activating Token Index: 602