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

Dataset: The Pile

Neuron 3506 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7303. Min Range: -5.7303

Max Act: 5.7303. Min Act: -0.0000

Data Index: 579530 (The Pile)

Max Activating Token Index: 470

Text #1

Max Range: 5.7303. Min Range: -5.7303

Max Act: 5.2104. Min Act: -0.0000

Data Index: 1638642 (The Pile)

Max Activating Token Index: 662

Text #2

Max Range: 5.7303. Min Range: -5.7303

Max Act: 5.1703. Min Act: -0.0000

Data Index: 1813042 (The Pile)

Max Activating Token Index: 366

Text #3

Max Range: 5.7303. Min Range: -5.7303

Max Act: 4.6855. Min Act: -0.0000

Data Index: 1940540 (The Pile)

Max Activating Token Index: 515

Text #4

Max Range: 5.7303. Min Range: -5.7303

Max Act: 4.6639. Min Act: -0.0000

Data Index: 1454957 (The Pile)

Max Activating Token Index: 138

Text #5

Max Range: 5.7303. Min Range: -5.7303

Max Act: 4.0848. Min Act: -0.0000

Data Index: 1888822 (The Pile)

Max Activating Token Index: 734

Text #6

Max Range: 5.7303. Min Range: -5.7303

Max Act: 3.9551. Min Act: -0.0000

Data Index: 441127 (The Pile)

Max Activating Token Index: 581

Text #7

Max Range: 5.7303. Min Range: -5.7303

Max Act: 3.9012. Min Act: -0.0000

Data Index: 660912 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 5.7303. Min Range: -5.7303

Max Act: 3.8778. Min Act: -0.0000

Data Index: 1183893 (The Pile)

Max Activating Token Index: 157

Text #9

Max Range: 5.7303. Min Range: -5.7303

Max Act: 3.7577. Min Act: -0.0000

Data Index: 731402 (The Pile)

Max Activating Token Index: 603

Text #10

Max Range: 5.7303. Min Range: -5.7303

Max Act: 4.0924. Min Act: -0.0000

Data Index: 876107 (The Pile)

Max Activating Token Index: 55

Text #11

Max Range: 5.7303. Min Range: -5.7303

Max Act: 4.0978. Min Act: -0.0000

Data Index: 1681983 (The Pile)

Max Activating Token Index: 65

Text #12

Max Range: 5.7303. Min Range: -5.7303

Max Act: 3.5481. Min Act: -0.0000

Data Index: 1003914 (The Pile)

Max Activating Token Index: 296

Text #13

Max Range: 5.7303. Min Range: -5.7303

Max Act: 3.7119. Min Act: -0.0000

Data Index: 78727 (The Pile)

Max Activating Token Index: 119

Text #14

Max Range: 5.7303. Min Range: -5.7303

Max Act: 3.7063. Min Act: -0.0000

Data Index: 1361017 (The Pile)

Max Activating Token Index: 437

Text #15

Max Range: 5.7303. Min Range: -5.7303

Max Act: 3.8435. Min Act: -0.0000

Data Index: 975804 (The Pile)

Max Activating Token Index: 318

Text #16

Max Range: 5.7303. Min Range: -5.7303

Max Act: 3.6765. Min Act: -0.0000

Data Index: 1887821 (The Pile)

Max Activating Token Index: 225

Text #17

Max Range: 5.7303. Min Range: -5.7303

Max Act: 3.6069. Min Act: -0.0000

Data Index: 1205371 (The Pile)

Max Activating Token Index: 620

Text #18

Max Range: 5.7303. Min Range: -5.7303

Max Act: 3.5445. Min Act: -0.0000

Data Index: 1160300 (The Pile)

Max Activating Token Index: 281

Text #19

Max Range: 5.7303. Min Range: -5.7303

Max Act: 3.3510. Min Act: -0.0000

Data Index: 1012296 (The Pile)

Max Activating Token Index: 395