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

Dataset: The Pile

Neuron 644 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.5331. Min Act: -0.0000

Data Index: 379154 (The Pile)

Max Activating Token Index: 651

Text #1

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3766. Min Act: -0.0000

Data Index: 1482104 (The Pile)

Max Activating Token Index: 708

Text #2

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1686404 (The Pile)

Max Activating Token Index: 558

Text #3

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1516234 (The Pile)

Max Activating Token Index: 871

Text #4

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3822. Min Act: -0.0000

Data Index: 235371 (The Pile)

Max Activating Token Index: 772

Text #5

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1441239 (The Pile)

Max Activating Token Index: 358

Text #6

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1622246 (The Pile)

Max Activating Token Index: 110

Text #7

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3112. Min Act: -0.0000

Data Index: 1749716 (The Pile)

Max Activating Token Index: 556

Text #8

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3315. Min Act: -0.0000

Data Index: 1004668 (The Pile)

Max Activating Token Index: 892

Text #9

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1946759 (The Pile)

Max Activating Token Index: 295

Text #10

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3012. Min Act: -0.0000

Data Index: 1771942 (The Pile)

Max Activating Token Index: 855

Text #11

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.3215. Min Act: -0.0000

Data Index: 719127 (The Pile)

Max Activating Token Index: 481

Text #12

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.2980. Min Act: -0.0000

Data Index: 714029 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1290168 (The Pile)

Max Activating Token Index: 740

Text #14

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.2991. Min Act: -0.0000

Data Index: 298262 (The Pile)

Max Activating Token Index: 229

Text #15

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.2740. Min Act: -0.0000

Data Index: 676914 (The Pile)

Max Activating Token Index: 813

Text #16

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.2857. Min Act: -0.0000

Data Index: 960738 (The Pile)

Max Activating Token Index: 252

Text #17

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.2816. Min Act: -0.0000

Data Index: 1373898 (The Pile)

Max Activating Token Index: 586

Text #18

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.2573. Min Act: -0.0000

Data Index: 262285 (The Pile)

Max Activating Token Index: 759

Text #19

Max Range: 0.5331. Min Range: -0.5331

Max Act: 0.2748. Min Act: -0.0000

Data Index: 774267 (The Pile)

Max Activating Token Index: 295