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

Dataset: The Pile

Neuron 4948 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: 4.2703. Min Range: -4.2703

Max Act: 4.2703. Min Act: -0.0000

Data Index: 407911 (The Pile)

Max Activating Token Index: 215

Text #1

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.7658. Min Act: -0.0000

Data Index: 238306 (The Pile)

Max Activating Token Index: 392

Text #2

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.4378. Min Act: -0.0000

Data Index: 1734163 (The Pile)

Max Activating Token Index: 884

Text #3

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.5776. Min Act: -0.0000

Data Index: 1504857 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.4328. Min Act: -0.0000

Data Index: 1844665 (The Pile)

Max Activating Token Index: 18

Text #5

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.2021. Min Act: -0.0000

Data Index: 1499849 (The Pile)

Max Activating Token Index: 905

Text #6

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.3558. Min Act: -0.0000

Data Index: 1710828 (The Pile)

Max Activating Token Index: 27

Text #7

Max Range: 4.2703. Min Range: -4.2703

Max Act: 2.8368. Min Act: -0.0000

Data Index: 52409 (The Pile)

Max Activating Token Index: 892

Text #8

Max Range: 4.2703. Min Range: -4.2703

Max Act: 2.9538. Min Act: -0.0000

Data Index: 1266542 (The Pile)

Max Activating Token Index: 61

Text #9

Max Range: 4.2703. Min Range: -4.2703

Max Act: 2.8670. Min Act: -0.0000

Data Index: 609688 (The Pile)

Max Activating Token Index: 39

Text #10

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.0028. Min Act: -0.0000

Data Index: 1807424 (The Pile)

Max Activating Token Index: 273

Text #11

Max Range: 4.2703. Min Range: -4.2703

Max Act: 2.8217. Min Act: -0.0000

Data Index: 1961227 (The Pile)

Max Activating Token Index: 81

Text #12

Max Range: 4.2703. Min Range: -4.2703

Max Act: 2.9303. Min Act: -0.0000

Data Index: 1099772 (The Pile)

Max Activating Token Index: 27

Text #13

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.3183. Min Act: -0.0000

Data Index: 1930840 (The Pile)

Max Activating Token Index: 774

Text #14

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.0293. Min Act: -0.0000

Data Index: 1405998 (The Pile)

Max Activating Token Index: 371

Text #15

Max Range: 4.2703. Min Range: -4.2703

Max Act: 2.7248. Min Act: -0.0000

Data Index: 547436 (The Pile)

Max Activating Token Index: 515

Text #16

Max Range: 4.2703. Min Range: -4.2703

Max Act: 2.8619. Min Act: -0.0000

Data Index: 419092 (The Pile)

Max Activating Token Index: 125

Text #17

Max Range: 4.2703. Min Range: -4.2703

Max Act: 2.8473. Min Act: -0.0000

Data Index: 1197917 (The Pile)

Max Activating Token Index: 128

Text #18

Max Range: 4.2703. Min Range: -4.2703

Max Act: 2.8398. Min Act: -0.0000

Data Index: 1462508 (The Pile)

Max Activating Token Index: 843

Text #19

Max Range: 4.2703. Min Range: -4.2703

Max Act: 2.7018. Min Act: -0.0000

Data Index: 1001735 (The Pile)

Max Activating Token Index: 232