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

Dataset: The Pile

Neuron 2370 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: 0.3752. Min Range: -0.3752

Max Act: 0.3752. Min Act: -0.0000

Data Index: 1775281 (The Pile)

Max Activating Token Index: 49

Text #1

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.3451. Min Act: -0.0000

Data Index: 1747004 (The Pile)

Max Activating Token Index: 268

Text #2

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.3294. Min Act: -0.0000

Data Index: 783685 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.3285. Min Act: -0.0000

Data Index: 1428593 (The Pile)

Max Activating Token Index: 370

Text #4

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.3034. Min Act: -0.0000

Data Index: 97069 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.3004. Min Act: -0.0000

Data Index: 1325019 (The Pile)

Max Activating Token Index: 905

Text #6

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.3024. Min Act: -0.0000

Data Index: 1168291 (The Pile)

Max Activating Token Index: 579

Text #7

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2657. Min Act: -0.0000

Data Index: 153753 (The Pile)

Max Activating Token Index: 644

Text #8

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.3207. Min Act: -0.0000

Data Index: 1091672 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2838. Min Act: -0.0000

Data Index: 469857 (The Pile)

Max Activating Token Index: 125

Text #10

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2940. Min Act: -0.0000

Data Index: 447008 (The Pile)

Max Activating Token Index: 511

Text #11

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2798. Min Act: -0.0000

Data Index: 1705200 (The Pile)

Max Activating Token Index: 745

Text #12

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2849. Min Act: -0.0000

Data Index: 1885074 (The Pile)

Max Activating Token Index: 499

Text #13

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2834. Min Act: -0.0000

Data Index: 678585 (The Pile)

Max Activating Token Index: 379

Text #14

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2868. Min Act: -0.0000

Data Index: 1724414 (The Pile)

Max Activating Token Index: 289

Text #15

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1309727 (The Pile)

Max Activating Token Index: 601

Text #16

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2651. Min Act: -0.0000

Data Index: 1796518 (The Pile)

Max Activating Token Index: 925

Text #17

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2763. Min Act: -0.0000

Data Index: 1246221 (The Pile)

Max Activating Token Index: 495

Text #18

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2773. Min Act: -0.0000

Data Index: 471005 (The Pile)

Max Activating Token Index: 594

Text #19

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1196040 (The Pile)

Max Activating Token Index: 417