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

Dataset: The Pile

Neuron 5027 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: 1.0308. Min Range: -1.0308

Max Act: 1.0308. Min Act: -0.0000

Data Index: 772842 (The Pile)

Max Activating Token Index: 406

Text #1

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.9667. Min Act: -0.0000

Data Index: 216403 (The Pile)

Max Activating Token Index: 1014

Text #2

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.8026. Min Act: -0.0000

Data Index: 1284695 (The Pile)

Max Activating Token Index: 756

Text #3

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.9470. Min Act: -0.0000

Data Index: 381081 (The Pile)

Max Activating Token Index: 55

Text #4

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.8800. Min Act: -0.0000

Data Index: 1558108 (The Pile)

Max Activating Token Index: 444

Text #5

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.7747. Min Act: -0.0000

Data Index: 1158005 (The Pile)

Max Activating Token Index: 922

Text #6

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.8366. Min Act: -0.0000

Data Index: 1871837 (The Pile)

Max Activating Token Index: 544

Text #7

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.7873. Min Act: -0.0000

Data Index: 1812417 (The Pile)

Max Activating Token Index: 295

Text #8

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.7206. Min Act: -0.0000

Data Index: 1876221 (The Pile)

Max Activating Token Index: 348

Text #9

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.7544. Min Act: -0.0000

Data Index: 557337 (The Pile)

Max Activating Token Index: 499

Text #10

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.7556. Min Act: -0.0000

Data Index: 1533590 (The Pile)

Max Activating Token Index: 380

Text #11

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.7247. Min Act: -0.0000

Data Index: 137534 (The Pile)

Max Activating Token Index: 556

Text #12

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.6844. Min Act: -0.0000

Data Index: 156570 (The Pile)

Max Activating Token Index: 774

Text #13

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1017413 (The Pile)

Max Activating Token Index: 228

Text #14

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.6289. Min Act: -0.0000

Data Index: 73031 (The Pile)

Max Activating Token Index: 949

Text #15

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.8047. Min Act: -0.0000

Data Index: 548948 (The Pile)

Max Activating Token Index: 197

Text #16

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.6110. Min Act: -0.0000

Data Index: 787496 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1161793 (The Pile)

Max Activating Token Index: 945

Text #18

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.5756. Min Act: -0.0000

Data Index: 759230 (The Pile)

Max Activating Token Index: 817

Text #19

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.6922. Min Act: -0.0000

Data Index: 834231 (The Pile)

Max Activating Token Index: 977