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

Dataset: The Pile

Neuron 1943 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1611351 (The Pile)

Max Activating Token Index: 378

Text #1

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5875. Min Act: -0.0000

Data Index: 192179 (The Pile)

Max Activating Token Index: 571

Text #2

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5363. Min Act: -0.0000

Data Index: 1431474 (The Pile)

Max Activating Token Index: 870

Text #3

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1642601 (The Pile)

Max Activating Token Index: 684

Text #4

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5420. Min Act: -0.0000

Data Index: 923421 (The Pile)

Max Activating Token Index: 221

Text #5

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5277. Min Act: -0.0000

Data Index: 500019 (The Pile)

Max Activating Token Index: 702

Text #6

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1480760 (The Pile)

Max Activating Token Index: 937

Text #7

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4849. Min Act: -0.0000

Data Index: 400737 (The Pile)

Max Activating Token Index: 738

Text #8

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4984. Min Act: 0.0001

Data Index: 917060 (The Pile)

Max Activating Token Index: 111

Text #9

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4917. Min Act: -0.0000

Data Index: 935365 (The Pile)

Max Activating Token Index: 912

Text #10

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4758. Min Act: 0.0001

Data Index: 40639 (The Pile)

Max Activating Token Index: 150

Text #11

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1001757 (The Pile)

Max Activating Token Index: 688

Text #12

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1318765 (The Pile)

Max Activating Token Index: 921

Text #13

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4412. Min Act: -0.0000

Data Index: 676284 (The Pile)

Max Activating Token Index: 229

Text #14

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4341. Min Act: -0.0000

Data Index: 627170 (The Pile)

Max Activating Token Index: 765

Text #15

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1500270 (The Pile)

Max Activating Token Index: 288

Text #16

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1881778 (The Pile)

Max Activating Token Index: 554

Text #17

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4308. Min Act: -0.0000

Data Index: 1211150 (The Pile)

Max Activating Token Index: 612

Text #18

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4455. Min Act: -0.0000

Data Index: 1622570 (The Pile)

Max Activating Token Index: 249

Text #19

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4458. Min Act: -0.0000

Data Index: 501294 (The Pile)

Max Activating Token Index: 895