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

Dataset: The Pile

Neuron 1459 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.4541. Min Act: -0.0000

Data Index: 696522 (The Pile)

Max Activating Token Index: 1008

Text #1

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.0858. Min Act: -0.0000

Data Index: 73487 (The Pile)

Max Activating Token Index: 687

Text #2

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.7608. Min Act: -0.0000

Data Index: 1930672 (The Pile)

Max Activating Token Index: 664

Text #3

Max Range: 4.7608. Min Range: -4.7608

Max Act: 3.7591. Min Act: -0.0000

Data Index: 834070 (The Pile)

Max Activating Token Index: 378

Text #4

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.0729. Min Act: -0.0000

Data Index: 333136 (The Pile)

Max Activating Token Index: 676

Text #5

Max Range: 4.7608. Min Range: -4.7608

Max Act: 3.7903. Min Act: -0.0000

Data Index: 474293 (The Pile)

Max Activating Token Index: 296

Text #6

Max Range: 4.7608. Min Range: -4.7608

Max Act: 3.1399. Min Act: -0.0000

Data Index: 210032 (The Pile)

Max Activating Token Index: 982

Text #7

Max Range: 4.7608. Min Range: -4.7608

Max Act: 3.3781. Min Act: -0.0000

Data Index: 1788380 (The Pile)

Max Activating Token Index: 212

Text #8

Max Range: 4.7608. Min Range: -4.7608

Max Act: 3.2138. Min Act: -0.0000

Data Index: 1701741 (The Pile)

Max Activating Token Index: 345

Text #9

Max Range: 4.7608. Min Range: -4.7608

Max Act: 3.0571. Min Act: -0.0000

Data Index: 30716 (The Pile)

Max Activating Token Index: 416

Text #10

Max Range: 4.7608. Min Range: -4.7608

Max Act: 3.3358. Min Act: -0.0000

Data Index: 479808 (The Pile)

Max Activating Token Index: 296

Text #11

Max Range: 4.7608. Min Range: -4.7608

Max Act: 2.9872. Min Act: -0.0000

Data Index: 160780 (The Pile)

Max Activating Token Index: 948

Text #12

Max Range: 4.7608. Min Range: -4.7608

Max Act: 3.5394. Min Act: -0.0000

Data Index: 1899397 (The Pile)

Max Activating Token Index: 989

Text #13

Max Range: 4.7608. Min Range: -4.7608

Max Act: 3.2300. Min Act: -0.0000

Data Index: 1611785 (The Pile)

Max Activating Token Index: 174

Text #14

Max Range: 4.7608. Min Range: -4.7608

Max Act: 3.0410. Min Act: -0.0000

Data Index: 124099 (The Pile)

Max Activating Token Index: 270

Text #15

Max Range: 4.7608. Min Range: -4.7608

Max Act: 3.0396. Min Act: -0.0000

Data Index: 1712631 (The Pile)

Max Activating Token Index: 296

Text #16

Max Range: 4.7608. Min Range: -4.7608

Max Act: 2.9960. Min Act: -0.0000

Data Index: 707824 (The Pile)

Max Activating Token Index: 268

Text #17

Max Range: 4.7608. Min Range: -4.7608

Max Act: 2.8398. Min Act: -0.0000

Data Index: 865058 (The Pile)

Max Activating Token Index: 601

Text #18

Max Range: 4.7608. Min Range: -4.7608

Max Act: 2.6813. Min Act: -0.0000

Data Index: 1175660 (The Pile)

Max Activating Token Index: 374

Text #19

Max Range: 4.7608. Min Range: -4.7608

Max Act: 2.3103. Min Act: -0.0000

Data Index: 136052 (The Pile)

Max Activating Token Index: 1021