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

Dataset: The Pile

Neuron 1572 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.6041. Min Act: -0.0000

Data Index: 1061186 (The Pile)

Max Activating Token Index: 565

Text #1

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.4893. Min Act: -0.0000

Data Index: 599903 (The Pile)

Max Activating Token Index: 56

Text #2

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.4648. Min Act: -0.0000

Data Index: 176920 (The Pile)

Max Activating Token Index: 264

Text #3

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3379. Min Act: -0.0000

Data Index: 967767 (The Pile)

Max Activating Token Index: 75

Text #4

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3571. Min Act: -0.0000

Data Index: 1152495 (The Pile)

Max Activating Token Index: 845

Text #5

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1993977 (The Pile)

Max Activating Token Index: 41

Text #6

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.4130. Min Act: -0.0000

Data Index: 1312647 (The Pile)

Max Activating Token Index: 420

Text #7

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3821. Min Act: -0.0000

Data Index: 1253032 (The Pile)

Max Activating Token Index: 550

Text #8

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.4096. Min Act: -0.0000

Data Index: 1007868 (The Pile)

Max Activating Token Index: 439

Text #9

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3605. Min Act: -0.0000

Data Index: 1860177 (The Pile)

Max Activating Token Index: 97

Text #10

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3754. Min Act: -0.0000

Data Index: 1853479 (The Pile)

Max Activating Token Index: 991

Text #11

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3233. Min Act: -0.0000

Data Index: 132803 (The Pile)

Max Activating Token Index: 804

Text #12

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3766. Min Act: -0.0000

Data Index: 1591092 (The Pile)

Max Activating Token Index: 805

Text #13

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1184508 (The Pile)

Max Activating Token Index: 255

Text #14

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1022756 (The Pile)

Max Activating Token Index: 584

Text #15

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3922. Min Act: -0.0001

Data Index: 1925138 (The Pile)

Max Activating Token Index: 10

Text #16

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3380. Min Act: -0.0000

Data Index: 608725 (The Pile)

Max Activating Token Index: 599

Text #17

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.2806. Min Act: -0.0000

Data Index: 913895 (The Pile)

Max Activating Token Index: 773

Text #18

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3302. Min Act: -0.0000

Data Index: 369917 (The Pile)

Max Activating Token Index: 520

Text #19

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1640810 (The Pile)

Max Activating Token Index: 881