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

Dataset: The Pile

Neuron 2556 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.6429. Min Act: -0.0000

Data Index: 1373378 (The Pile)

Max Activating Token Index: 286

Text #1

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.4445. Min Act: -0.0000

Data Index: 272864 (The Pile)

Max Activating Token Index: 383

Text #2

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.0609. Min Act: -0.0000

Data Index: 1282603 (The Pile)

Max Activating Token Index: 15

Text #3

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.1115. Min Act: -0.0000

Data Index: 1502295 (The Pile)

Max Activating Token Index: 487

Text #4

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.0817. Min Act: -0.0000

Data Index: 1760771 (The Pile)

Max Activating Token Index: 366

Text #5

Max Range: 1.6429. Min Range: -1.6429

Max Act: 0.9784. Min Act: -0.0000

Data Index: 1891417 (The Pile)

Max Activating Token Index: 676

Text #6

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1284395 (The Pile)

Max Activating Token Index: 518

Text #7

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.0003. Min Act: -0.0000

Data Index: 595840 (The Pile)

Max Activating Token Index: 169

Text #8

Max Range: 1.6429. Min Range: -1.6429

Max Act: 0.9321. Min Act: -0.0000

Data Index: 778660 (The Pile)

Max Activating Token Index: 162

Text #9

Max Range: 1.6429. Min Range: -1.6429

Max Act: 0.9559. Min Act: -0.0000

Data Index: 363062 (The Pile)

Max Activating Token Index: 303

Text #10

Max Range: 1.6429. Min Range: -1.6429

Max Act: 0.9657. Min Act: -0.0000

Data Index: 103429 (The Pile)

Max Activating Token Index: 377

Text #11

Max Range: 1.6429. Min Range: -1.6429

Max Act: 0.9335. Min Act: -0.0000

Data Index: 606326 (The Pile)

Max Activating Token Index: 589

Text #12

Max Range: 1.6429. Min Range: -1.6429

Max Act: 0.9243. Min Act: -0.0000

Data Index: 1358251 (The Pile)

Max Activating Token Index: 587

Text #13

Max Range: 1.6429. Min Range: -1.6429

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1821558 (The Pile)

Max Activating Token Index: 74

Text #14

Max Range: 1.6429. Min Range: -1.6429

Max Act: 0.9094. Min Act: -0.0000

Data Index: 1800167 (The Pile)

Max Activating Token Index: 228

Text #15

Max Range: 1.6429. Min Range: -1.6429

Max Act: 0.8367. Min Act: -0.0000

Data Index: 1167160 (The Pile)

Max Activating Token Index: 63

Text #16

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.0254. Min Act: -0.0000

Data Index: 1740367 (The Pile)

Max Activating Token Index: 61

Text #17

Max Range: 1.6429. Min Range: -1.6429

Max Act: 0.8839. Min Act: -0.0000

Data Index: 222788 (The Pile)

Max Activating Token Index: 671

Text #18

Max Range: 1.6429. Min Range: -1.6429

Max Act: 0.9557. Min Act: -0.0000

Data Index: 1442396 (The Pile)

Max Activating Token Index: 841

Text #19

Max Range: 1.6429. Min Range: -1.6429

Max Act: 0.8895. Min Act: -0.0000

Data Index: 1968323 (The Pile)

Max Activating Token Index: 74