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

Dataset: The Pile

Neuron 3695 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: 1.9468. Min Range: -1.9468

Max Act: 1.9468. Min Act: -0.0000

Data Index: 1540490 (The Pile)

Max Activating Token Index: 681

Text #1

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.7100. Min Act: -0.0000

Data Index: 878547 (The Pile)

Max Activating Token Index: 922

Text #2

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.5646. Min Act: -0.0000

Data Index: 287416 (The Pile)

Max Activating Token Index: 978

Text #3

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.6805. Min Act: -0.0000

Data Index: 1259143 (The Pile)

Max Activating Token Index: 449

Text #4

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.5725. Min Act: -0.0000

Data Index: 779860 (The Pile)

Max Activating Token Index: 388

Text #5

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.6711. Min Act: -0.0000

Data Index: 840076 (The Pile)

Max Activating Token Index: 598

Text #6

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.5676. Min Act: -0.0000

Data Index: 1114949 (The Pile)

Max Activating Token Index: 1012

Text #7

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.3869. Min Act: -0.0000

Data Index: 586140 (The Pile)

Max Activating Token Index: 812

Text #8

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.3405. Min Act: -0.0000

Data Index: 366677 (The Pile)

Max Activating Token Index: 886

Text #9

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.3722. Min Act: -0.0000

Data Index: 1094479 (The Pile)

Max Activating Token Index: 847

Text #10

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.3793. Min Act: -0.0000

Data Index: 563550 (The Pile)

Max Activating Token Index: 963

Text #11

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.2317. Min Act: -0.0000

Data Index: 874706 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.2224. Min Act: -0.0000

Data Index: 144035 (The Pile)

Max Activating Token Index: 465

Text #13

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.1494. Min Act: -0.0000

Data Index: 34164 (The Pile)

Max Activating Token Index: 881

Text #14

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.1932. Min Act: -0.0000

Data Index: 624244 (The Pile)

Max Activating Token Index: 54

Text #15

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.2746. Min Act: -0.0000

Data Index: 974782 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.2008. Min Act: -0.0000

Data Index: 346450 (The Pile)

Max Activating Token Index: 663

Text #17

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.2713. Min Act: -0.0000

Data Index: 1060514 (The Pile)

Max Activating Token Index: 874

Text #18

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.2515. Min Act: -0.0000

Data Index: 1249769 (The Pile)

Max Activating Token Index: 506

Text #19

Max Range: 1.9468. Min Range: -1.9468

Max Act: 1.2181. Min Act: -0.0000

Data Index: 1539674 (The Pile)

Max Activating Token Index: 553