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

Dataset: The Pile

Neuron 3017 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.8775. Min Act: -0.0000

Data Index: 1707724 (The Pile)

Max Activating Token Index: 492

Text #1

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.6112. Min Act: -0.0000

Data Index: 624782 (The Pile)

Max Activating Token Index: 973

Text #2

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.6325. Min Act: 0.0000

Data Index: 1711646 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.6324. Min Act: -0.0000

Data Index: 1438432 (The Pile)

Max Activating Token Index: 91

Text #4

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.6553. Min Act: -0.0000

Data Index: 833254 (The Pile)

Max Activating Token Index: 138

Text #5

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.7257. Min Act: -0.0000

Data Index: 1438786 (The Pile)

Max Activating Token Index: 582

Text #6

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.3776. Min Act: -0.0000

Data Index: 1056841 (The Pile)

Max Activating Token Index: 850

Text #7

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.7751. Min Act: -0.0000

Data Index: 1024093 (The Pile)

Max Activating Token Index: 472

Text #8

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.5137. Min Act: -0.0000

Data Index: 447561 (The Pile)

Max Activating Token Index: 157

Text #9

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.5713. Min Act: -0.0000

Data Index: 1513713 (The Pile)

Max Activating Token Index: 630

Text #10

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.3661. Min Act: -0.0000

Data Index: 103616 (The Pile)

Max Activating Token Index: 283

Text #11

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.4397. Min Act: 0.0000

Data Index: 124219 (The Pile)

Max Activating Token Index: 673

Text #12

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.2902. Min Act: -0.0000

Data Index: 1711585 (The Pile)

Max Activating Token Index: 642

Text #13

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.4163. Min Act: 0.0000

Data Index: 1231641 (The Pile)

Max Activating Token Index: 29

Text #14

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.4013. Min Act: -0.0000

Data Index: 740933 (The Pile)

Max Activating Token Index: 588

Text #15

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.5025. Min Act: -0.0000

Data Index: 1986171 (The Pile)

Max Activating Token Index: 557

Text #16

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.2223. Min Act: -0.0000

Data Index: 583143 (The Pile)

Max Activating Token Index: 682

Text #17

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.3450. Min Act: -0.0000

Data Index: 1933398 (The Pile)

Max Activating Token Index: 687

Text #18

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.3773. Min Act: -0.0000

Data Index: 279351 (The Pile)

Max Activating Token Index: 216

Text #19

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.3512. Min Act: -0.0000

Data Index: 103508 (The Pile)

Max Activating Token Index: 93