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

Dataset: The Pile

Neuron 2600 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: 0.9232. Min Range: -0.9232

Max Act: 0.9232. Min Act: -0.0000

Data Index: 1228625 (The Pile)

Max Activating Token Index: 856

Text #1

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.8227. Min Act: -0.0000

Data Index: 1783946 (The Pile)

Max Activating Token Index: 806

Text #2

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.9066. Min Act: -0.0000

Data Index: 643456 (The Pile)

Max Activating Token Index: 646

Text #3

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.8432. Min Act: -0.0000

Data Index: 543445 (The Pile)

Max Activating Token Index: 731

Text #4

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.7470. Min Act: -0.0000

Data Index: 888986 (The Pile)

Max Activating Token Index: 679

Text #5

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.6860. Min Act: -0.0000

Data Index: 1936385 (The Pile)

Max Activating Token Index: 533

Text #6

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.7436. Min Act: -0.0000

Data Index: 427134 (The Pile)

Max Activating Token Index: 564

Text #7

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.7294. Min Act: -0.0000

Data Index: 567563 (The Pile)

Max Activating Token Index: 787

Text #8

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.6790. Min Act: -0.0000

Data Index: 351918 (The Pile)

Max Activating Token Index: 236

Text #9

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.7317. Min Act: -0.0000

Data Index: 874382 (The Pile)

Max Activating Token Index: 828

Text #10

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1280714 (The Pile)

Max Activating Token Index: 779

Text #11

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.7434. Min Act: -0.0000

Data Index: 553875 (The Pile)

Max Activating Token Index: 818

Text #12

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.6521. Min Act: -0.0000

Data Index: 1417244 (The Pile)

Max Activating Token Index: 867

Text #13

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.6923. Min Act: -0.0000

Data Index: 710448 (The Pile)

Max Activating Token Index: 648

Text #14

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.7103. Min Act: -0.0000

Data Index: 1130702 (The Pile)

Max Activating Token Index: 668

Text #15

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.6530. Min Act: -0.0000

Data Index: 840335 (The Pile)

Max Activating Token Index: 974

Text #16

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.6717. Min Act: -0.0000

Data Index: 1042295 (The Pile)

Max Activating Token Index: 235

Text #17

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.6289. Min Act: -0.0000

Data Index: 1062615 (The Pile)

Max Activating Token Index: 989

Text #18

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.6725. Min Act: -0.0000

Data Index: 1092775 (The Pile)

Max Activating Token Index: 163

Text #19

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.6298. Min Act: -0.0000

Data Index: 259727 (The Pile)

Max Activating Token Index: 591