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

Dataset: The Pile

Neuron 3278 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5642. Min Act: -0.0000

Data Index: 1482508 (The Pile)

Max Activating Token Index: 858

Text #1

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4626. Min Act: -0.0000

Data Index: 144282 (The Pile)

Max Activating Token Index: 491

Text #2

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4569. Min Act: -0.0000

Data Index: 399913 (The Pile)

Max Activating Token Index: 737

Text #3

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4087. Min Act: -0.0000

Data Index: 496984 (The Pile)

Max Activating Token Index: 969

Text #4

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1921864 (The Pile)

Max Activating Token Index: 624

Text #5

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4240. Min Act: -0.0000

Data Index: 767822 (The Pile)

Max Activating Token Index: 62

Text #6

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.3942. Min Act: -0.0000

Data Index: 76041 (The Pile)

Max Activating Token Index: 359

Text #7

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.3788. Min Act: -0.0000

Data Index: 1836454 (The Pile)

Max Activating Token Index: 440

Text #8

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.3648. Min Act: -0.0000

Data Index: 16248 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.3759. Min Act: -0.0000

Data Index: 964931 (The Pile)

Max Activating Token Index: 85

Text #10

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.3517. Min Act: -0.0000

Data Index: 1644391 (The Pile)

Max Activating Token Index: 808

Text #11

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.3992. Min Act: -0.0000

Data Index: 73384 (The Pile)

Max Activating Token Index: 722

Text #12

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.3516. Min Act: -0.0000

Data Index: 1494962 (The Pile)

Max Activating Token Index: 535

Text #13

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.3455. Min Act: -0.0000

Data Index: 1580757 (The Pile)

Max Activating Token Index: 714

Text #14

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.3421. Min Act: -0.0000

Data Index: 1362044 (The Pile)

Max Activating Token Index: 54

Text #15

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.3756. Min Act: -0.0000

Data Index: 1135249 (The Pile)

Max Activating Token Index: 178

Text #16

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.3443. Min Act: -0.0000

Data Index: 138824 (The Pile)

Max Activating Token Index: 961

Text #17

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.3483. Min Act: -0.0000

Data Index: 540728 (The Pile)

Max Activating Token Index: 423

Text #18

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.3233. Min Act: -0.0000

Data Index: 1843956 (The Pile)

Max Activating Token Index: 622

Text #19

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.3308. Min Act: -0.0000

Data Index: 1095378 (The Pile)

Max Activating Token Index: 142