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

Dataset: The Pile

Neuron 1799 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: 0.9755. Min Range: -0.9755

Max Act: 0.9755. Min Act: -0.0000

Data Index: 132641 (The Pile)

Max Activating Token Index: 446

Text #1

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7947. Min Act: -0.0000

Data Index: 43433 (The Pile)

Max Activating Token Index: 533

Text #2

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7855. Min Act: -0.0000

Data Index: 1135253 (The Pile)

Max Activating Token Index: 927

Text #3

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7594. Min Act: -0.0000

Data Index: 581522 (The Pile)

Max Activating Token Index: 101

Text #4

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.8081. Min Act: -0.0000

Data Index: 1498165 (The Pile)

Max Activating Token Index: 557

Text #5

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7662. Min Act: -0.0000

Data Index: 176941 (The Pile)

Max Activating Token Index: 254

Text #6

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7669. Min Act: -0.0000

Data Index: 277400 (The Pile)

Max Activating Token Index: 116

Text #7

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1499584 (The Pile)

Max Activating Token Index: 612

Text #8

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1876464 (The Pile)

Max Activating Token Index: 149

Text #9

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7818. Min Act: -0.0000

Data Index: 1773161 (The Pile)

Max Activating Token Index: 666

Text #10

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7165. Min Act: -0.0000

Data Index: 1500734 (The Pile)

Max Activating Token Index: 574

Text #11

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.6860. Min Act: -0.0000

Data Index: 1149834 (The Pile)

Max Activating Token Index: 127

Text #12

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7197. Min Act: -0.0000

Data Index: 423755 (The Pile)

Max Activating Token Index: 889

Text #13

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7370. Min Act: -0.0000

Data Index: 258575 (The Pile)

Max Activating Token Index: 582

Text #14

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7338. Min Act: -0.0000

Data Index: 1096258 (The Pile)

Max Activating Token Index: 528

Text #15

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.6497. Min Act: -0.0000

Data Index: 749011 (The Pile)

Max Activating Token Index: 768

Text #16

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1436564 (The Pile)

Max Activating Token Index: 344

Text #17

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.7194. Min Act: -0.0000

Data Index: 1178692 (The Pile)

Max Activating Token Index: 470

Text #18

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.6893. Min Act: -0.0000

Data Index: 473109 (The Pile)

Max Activating Token Index: 865

Text #19

Max Range: 0.9755. Min Range: -0.9755

Max Act: 0.6657. Min Act: -0.0000

Data Index: 756837 (The Pile)

Max Activating Token Index: 510