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

Dataset: The Pile

Neuron 1747 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: 1.5502. Min Range: -1.5502

Max Act: 1.5400. Min Act: -0.0000

Data Index: 304161 (The Pile)

Max Activating Token Index: 36

Text #1

Max Range: 1.5502. Min Range: -1.5502

Max Act: 1.5502. Min Act: -0.0000

Data Index: 1160170 (The Pile)

Max Activating Token Index: 597

Text #2

Max Range: 1.5502. Min Range: -1.5502

Max Act: 1.1992. Min Act: -0.0000

Data Index: 785328 (The Pile)

Max Activating Token Index: 955

Text #3

Max Range: 1.5502. Min Range: -1.5502

Max Act: 1.1532. Min Act: -0.0000

Data Index: 1372013 (The Pile)

Max Activating Token Index: 628

Text #4

Max Range: 1.5502. Min Range: -1.5502

Max Act: 1.1765. Min Act: -0.0000

Data Index: 1799557 (The Pile)

Max Activating Token Index: 309

Text #5

Max Range: 1.5502. Min Range: -1.5502

Max Act: 1.0465. Min Act: -0.0000

Data Index: 858643 (The Pile)

Max Activating Token Index: 937

Text #6

Max Range: 1.5502. Min Range: -1.5502

Max Act: 1.0301. Min Act: -0.0000

Data Index: 280048 (The Pile)

Max Activating Token Index: 369

Text #7

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.9881. Min Act: -0.0000

Data Index: 1467251 (The Pile)

Max Activating Token Index: 380

Text #8

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.8755. Min Act: -0.0000

Data Index: 1321793 (The Pile)

Max Activating Token Index: 809

Text #9

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.9260. Min Act: -0.0000

Data Index: 403770 (The Pile)

Max Activating Token Index: 543

Text #10

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.9543. Min Act: 0.0000

Data Index: 42570 (The Pile)

Max Activating Token Index: 34

Text #11

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.9013. Min Act: -0.0000

Data Index: 131908 (The Pile)

Max Activating Token Index: 573

Text #12

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.8149. Min Act: -0.0000

Data Index: 348717 (The Pile)

Max Activating Token Index: 603

Text #13

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.9062. Min Act: -0.0000

Data Index: 770466 (The Pile)

Max Activating Token Index: 398

Text #14

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.8228. Min Act: -0.0000

Data Index: 897430 (The Pile)

Max Activating Token Index: 852

Text #15

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.8799. Min Act: 0.0000

Data Index: 1591732 (The Pile)

Max Activating Token Index: 604

Text #16

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1308239 (The Pile)

Max Activating Token Index: 342

Text #17

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.8424. Min Act: -0.0000

Data Index: 880134 (The Pile)

Max Activating Token Index: 330

Text #18

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.8229. Min Act: -0.0000

Data Index: 541301 (The Pile)

Max Activating Token Index: 703

Text #19

Max Range: 1.5502. Min Range: -1.5502

Max Act: 0.8160. Min Act: -0.0000

Data Index: 1768515 (The Pile)

Max Activating Token Index: 391