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

Dataset: The Pile

Neuron 3890 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: 0.5571. Min Range: -0.5571

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1447644 (The Pile)

Max Activating Token Index: 849

Text #1

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3341. Min Act: -0.0000

Data Index: 606275 (The Pile)

Max Activating Token Index: 689

Text #2

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1753350 (The Pile)

Max Activating Token Index: 988

Text #3

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4056. Min Act: -0.0000

Data Index: 749352 (The Pile)

Max Activating Token Index: 937

Text #4

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3787. Min Act: -0.0000

Data Index: 912722 (The Pile)

Max Activating Token Index: 55

Text #5

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.2601. Min Act: -0.0000

Data Index: 44223 (The Pile)

Max Activating Token Index: 940

Text #6

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3433. Min Act: -0.0000

Data Index: 173322 (The Pile)

Max Activating Token Index: 715

Text #7

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3351. Min Act: -0.0000

Data Index: 1094567 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1745164 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3158. Min Act: -0.0000

Data Index: 287516 (The Pile)

Max Activating Token Index: 777

Text #10

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.2892. Min Act: -0.0000

Data Index: 94715 (The Pile)

Max Activating Token Index: 904

Text #11

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3157. Min Act: -0.0000

Data Index: 614516 (The Pile)

Max Activating Token Index: 984

Text #12

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3257. Min Act: -0.0000

Data Index: 651450 (The Pile)

Max Activating Token Index: 917

Text #13

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.2921. Min Act: -0.0000

Data Index: 867870 (The Pile)

Max Activating Token Index: 679

Text #14

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3065. Min Act: -0.0000

Data Index: 369212 (The Pile)

Max Activating Token Index: 330

Text #15

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3389. Min Act: -0.0000

Data Index: 7441 (The Pile)

Max Activating Token Index: 165

Text #16

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3059. Min Act: -0.0000

Data Index: 545607 (The Pile)

Max Activating Token Index: 525

Text #17

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3004. Min Act: -0.0000

Data Index: 1153881 (The Pile)

Max Activating Token Index: 750

Text #18

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1358366 (The Pile)

Max Activating Token Index: 493

Text #19

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.2910. Min Act: -0.0000

Data Index: 1517507 (The Pile)

Max Activating Token Index: 293