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

Dataset: The Pile

Neuron 4379 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: 0.9556. Min Range: -0.9556

Max Act: 0.9556. Min Act: -0.0000

Data Index: 834902 (The Pile)

Max Activating Token Index: 629

Text #1

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8942. Min Act: -0.0000

Data Index: 276107 (The Pile)

Max Activating Token Index: 569

Text #2

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.9466. Min Act: -0.0000

Data Index: 714303 (The Pile)

Max Activating Token Index: 204

Text #3

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8527. Min Act: -0.0000

Data Index: 983653 (The Pile)

Max Activating Token Index: 912

Text #4

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8682. Min Act: -0.0000

Data Index: 867326 (The Pile)

Max Activating Token Index: 869

Text #5

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8127. Min Act: -0.0000

Data Index: 1301750 (The Pile)

Max Activating Token Index: 546

Text #6

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.7539. Min Act: -0.0000

Data Index: 1860665 (The Pile)

Max Activating Token Index: 818

Text #7

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.7711. Min Act: -0.0000

Data Index: 659797 (The Pile)

Max Activating Token Index: 864

Text #8

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.7833. Min Act: -0.0000

Data Index: 1841911 (The Pile)

Max Activating Token Index: 207

Text #9

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8045. Min Act: -0.0000

Data Index: 530845 (The Pile)

Max Activating Token Index: 805

Text #10

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1579912 (The Pile)

Max Activating Token Index: 777

Text #11

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.6997. Min Act: -0.0000

Data Index: 1088240 (The Pile)

Max Activating Token Index: 571

Text #12

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.7334. Min Act: -0.0000

Data Index: 355027 (The Pile)

Max Activating Token Index: 581

Text #13

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.7320. Min Act: -0.0000

Data Index: 652689 (The Pile)

Max Activating Token Index: 25

Text #14

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.7591. Min Act: -0.0000

Data Index: 1307168 (The Pile)

Max Activating Token Index: 978

Text #15

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.7017. Min Act: -0.0000

Data Index: 603322 (The Pile)

Max Activating Token Index: 490

Text #16

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.7197. Min Act: -0.0000

Data Index: 1037589 (The Pile)

Max Activating Token Index: 366

Text #17

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.6974. Min Act: -0.0000

Data Index: 1253974 (The Pile)

Max Activating Token Index: 783

Text #18

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.6720. Min Act: -0.0000

Data Index: 257341 (The Pile)

Max Activating Token Index: 837

Text #19

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.6878. Min Act: -0.0000

Data Index: 666525 (The Pile)

Max Activating Token Index: 658