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

Dataset: The Pile

Neuron 2496 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: 1.2002. Min Range: -1.2002

Max Act: 1.2002. Min Act: -0.0000

Data Index: 122594 (The Pile)

Max Activating Token Index: 644

Text #1

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.0581. Min Act: -0.0000

Data Index: 1498435 (The Pile)

Max Activating Token Index: 912

Text #2

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.0157. Min Act: -0.0000

Data Index: 1578147 (The Pile)

Max Activating Token Index: 821

Text #3

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.0892. Min Act: -0.0000

Data Index: 1743928 (The Pile)

Max Activating Token Index: 486

Text #4

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.0220. Min Act: -0.0000

Data Index: 1928169 (The Pile)

Max Activating Token Index: 714

Text #5

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.0233. Min Act: -0.0000

Data Index: 460088 (The Pile)

Max Activating Token Index: 901

Text #6

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.0100. Min Act: -0.0000

Data Index: 1338475 (The Pile)

Max Activating Token Index: 49

Text #7

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.0016. Min Act: -0.0000

Data Index: 1403990 (The Pile)

Max Activating Token Index: 51

Text #8

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.9341. Min Act: -0.0000

Data Index: 1234755 (The Pile)

Max Activating Token Index: 390

Text #9

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.9350. Min Act: -0.0000

Data Index: 664470 (The Pile)

Max Activating Token Index: 436

Text #10

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.0635. Min Act: -0.0000

Data Index: 379990 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.0916. Min Act: -0.0000

Data Index: 1116896 (The Pile)

Max Activating Token Index: 632

Text #12

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.9314. Min Act: -0.0000

Data Index: 1552316 (The Pile)

Max Activating Token Index: 134

Text #13

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.8951. Min Act: -0.0000

Data Index: 828211 (The Pile)

Max Activating Token Index: 231

Text #14

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.9841. Min Act: -0.0000

Data Index: 15203 (The Pile)

Max Activating Token Index: 365

Text #15

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.0180. Min Act: -0.0000

Data Index: 1993048 (The Pile)

Max Activating Token Index: 999

Text #16

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.9687. Min Act: -0.0000

Data Index: 216786 (The Pile)

Max Activating Token Index: 855

Text #17

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1481310 (The Pile)

Max Activating Token Index: 648

Text #18

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1503461 (The Pile)

Max Activating Token Index: 414

Text #19

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.9460. Min Act: -0.0000

Data Index: 32705 (The Pile)

Max Activating Token Index: 321