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

Dataset: The Pile

Neuron 4760 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: 1.7651. Min Range: -1.7651

Max Act: 1.7651. Min Act: -0.0000

Data Index: 1902641 (The Pile)

Max Activating Token Index: 947

Text #1

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.2096. Min Act: -0.0000

Data Index: 1094579 (The Pile)

Max Activating Token Index: 374

Text #2

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.2737. Min Act: -0.0000

Data Index: 939434 (The Pile)

Max Activating Token Index: 17

Text #3

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.1439. Min Act: -0.0000

Data Index: 1207796 (The Pile)

Max Activating Token Index: 1009

Text #4

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.0476. Min Act: -0.0000

Data Index: 1892703 (The Pile)

Max Activating Token Index: 520

Text #5

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.2188. Min Act: -0.0000

Data Index: 392753 (The Pile)

Max Activating Token Index: 613

Text #6

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.1702. Min Act: -0.0000

Data Index: 1036407 (The Pile)

Max Activating Token Index: 798

Text #7

Max Range: 1.7651. Min Range: -1.7651

Max Act: 0.8971. Min Act: -0.0000

Data Index: 1428388 (The Pile)

Max Activating Token Index: 503

Text #8

Max Range: 1.7651. Min Range: -1.7651

Max Act: 0.8178. Min Act: -0.0000

Data Index: 255297 (The Pile)

Max Activating Token Index: 266

Text #9

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.0861. Min Act: -0.0000

Data Index: 105135 (The Pile)

Max Activating Token Index: 1009

Text #10

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.0725. Min Act: -0.0000

Data Index: 72477 (The Pile)

Max Activating Token Index: 55

Text #11

Max Range: 1.7651. Min Range: -1.7651

Max Act: 0.9022. Min Act: -0.0000

Data Index: 352966 (The Pile)

Max Activating Token Index: 158

Text #12

Max Range: 1.7651. Min Range: -1.7651

Max Act: 0.9370. Min Act: -0.0000

Data Index: 1781663 (The Pile)

Max Activating Token Index: 228

Text #13

Max Range: 1.7651. Min Range: -1.7651

Max Act: 0.9719. Min Act: -0.0000

Data Index: 228686 (The Pile)

Max Activating Token Index: 27

Text #14

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.0157. Min Act: -0.0000

Data Index: 1475847 (The Pile)

Max Activating Token Index: 60

Text #15

Max Range: 1.7651. Min Range: -1.7651

Max Act: 0.9889. Min Act: -0.0000

Data Index: 151625 (The Pile)

Max Activating Token Index: 850

Text #16

Max Range: 1.7651. Min Range: -1.7651

Max Act: 0.7478. Min Act: -0.0000

Data Index: 65273 (The Pile)

Max Activating Token Index: 847

Text #17

Max Range: 1.7651. Min Range: -1.7651

Max Act: 0.9439. Min Act: -0.0000

Data Index: 318420 (The Pile)

Max Activating Token Index: 787

Text #18

Max Range: 1.7651. Min Range: -1.7651

Max Act: 0.9459. Min Act: -0.0000

Data Index: 83835 (The Pile)

Max Activating Token Index: 239

Text #19

Max Range: 1.7651. Min Range: -1.7651

Max Act: 0.9308. Min Act: -0.0000

Data Index: 1136613 (The Pile)

Max Activating Token Index: 172