Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2939 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.3459. Min Act: -0.0000

Data Index: 1603734 (The Pile)

Max Activating Token Index: 114

Text #1

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.3271. Min Act: -0.0000

Data Index: 1328040 (The Pile)

Max Activating Token Index: 977

Text #2

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2838. Min Act: -0.0000

Data Index: 331503 (The Pile)

Max Activating Token Index: 358

Text #3

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2492. Min Act: -0.0000

Data Index: 1065542 (The Pile)

Max Activating Token Index: 479

Text #4

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2412. Min Act: -0.0000

Data Index: 997734 (The Pile)

Max Activating Token Index: 550

Text #5

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2220. Min Act: -0.0000

Data Index: 360461 (The Pile)

Max Activating Token Index: 626

Text #6

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2156. Min Act: -0.0000

Data Index: 186327 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2146. Min Act: -0.0000

Data Index: 135151 (The Pile)

Max Activating Token Index: 396

Text #8

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2001. Min Act: 0.0000

Data Index: 184752 (The Pile)

Max Activating Token Index: 650

Text #9

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2162. Min Act: -0.0000

Data Index: 387064 (The Pile)

Max Activating Token Index: 1022

Text #10

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2072. Min Act: 0.0000

Data Index: 824810 (The Pile)

Max Activating Token Index: 278

Text #11

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.1879. Min Act: -0.0000

Data Index: 1853950 (The Pile)

Max Activating Token Index: 49

Text #12

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.1912. Min Act: -0.0000

Data Index: 1544761 (The Pile)

Max Activating Token Index: 477

Text #13

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1908346 (The Pile)

Max Activating Token Index: 308

Text #14

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.1748. Min Act: -0.0000

Data Index: 827515 (The Pile)

Max Activating Token Index: 494

Text #15

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.1756. Min Act: -0.0000

Data Index: 1563774 (The Pile)

Max Activating Token Index: 380

Text #16

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.1824. Min Act: -0.0000

Data Index: 137609 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.1856. Min Act: -0.0000

Data Index: 322101 (The Pile)

Max Activating Token Index: 775

Text #18

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.1744. Min Act: -0.0000

Data Index: 1285505 (The Pile)

Max Activating Token Index: 251

Text #19

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.1778. Min Act: -0.0000

Data Index: 448108 (The Pile)

Max Activating Token Index: 387