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

Dataset: The Pile

Neuron 4156 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4948. Min Act: -0.0000

Data Index: 849995 (The Pile)

Max Activating Token Index: 856

Text #1

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1431067 (The Pile)

Max Activating Token Index: 312

Text #2

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4321. Min Act: -0.0000

Data Index: 1847550 (The Pile)

Max Activating Token Index: 733

Text #3

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1987992 (The Pile)

Max Activating Token Index: 169

Text #4

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1191297 (The Pile)

Max Activating Token Index: 442

Text #5

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3772. Min Act: -0.0000

Data Index: 1427615 (The Pile)

Max Activating Token Index: 999

Text #6

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3894. Min Act: -0.0000

Data Index: 1985430 (The Pile)

Max Activating Token Index: 193

Text #7

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4261. Min Act: -0.0000

Data Index: 789822 (The Pile)

Max Activating Token Index: 802

Text #8

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3761. Min Act: -0.0000

Data Index: 388376 (The Pile)

Max Activating Token Index: 49

Text #9

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3839. Min Act: -0.0000

Data Index: 571668 (The Pile)

Max Activating Token Index: 489

Text #10

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.4005. Min Act: -0.0000

Data Index: 1785856 (The Pile)

Max Activating Token Index: 545

Text #11

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3857. Min Act: -0.0000

Data Index: 1674666 (The Pile)

Max Activating Token Index: 1016

Text #12

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3871. Min Act: -0.0000

Data Index: 13960 (The Pile)

Max Activating Token Index: 453

Text #13

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3727. Min Act: -0.0000

Data Index: 807260 (The Pile)

Max Activating Token Index: 176

Text #14

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1662803 (The Pile)

Max Activating Token Index: 914

Text #15

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3777. Min Act: -0.0000

Data Index: 970938 (The Pile)

Max Activating Token Index: 493

Text #16

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3765. Min Act: -0.0000

Data Index: 884176 (The Pile)

Max Activating Token Index: 619

Text #17

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1055940 (The Pile)

Max Activating Token Index: 330

Text #18

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3717. Min Act: -0.0000

Data Index: 342068 (The Pile)

Max Activating Token Index: 446

Text #19

Max Range: 0.4948. Min Range: -0.4948

Max Act: 0.3706. Min Act: -0.0000

Data Index: 1570986 (The Pile)

Max Activating Token Index: 145