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

Dataset: The Pile

Neuron 3635 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: 3.9864. Min Range: -3.9864

Max Act: 3.8650. Min Act: -0.0000

Data Index: 1194843 (The Pile)

Max Activating Token Index: 125

Text #1

Max Range: 3.9864. Min Range: -3.9864

Max Act: 3.4110. Min Act: -0.0000

Data Index: 966133 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 3.9864. Min Range: -3.9864

Max Act: 3.7096. Min Act: -0.0000

Data Index: 366593 (The Pile)

Max Activating Token Index: 64

Text #3

Max Range: 3.9864. Min Range: -3.9864

Max Act: 3.9864. Min Act: -0.0000

Data Index: 934712 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 3.9864. Min Range: -3.9864

Max Act: 3.9137. Min Act: -0.0000

Data Index: 16352 (The Pile)

Max Activating Token Index: 40

Text #5

Max Range: 3.9864. Min Range: -3.9864

Max Act: 3.8642. Min Act: -0.0000

Data Index: 703729 (The Pile)

Max Activating Token Index: 114

Text #6

Max Range: 3.9864. Min Range: -3.9864

Max Act: 3.5769. Min Act: -0.0000

Data Index: 584680 (The Pile)

Max Activating Token Index: 664

Text #7

Max Range: 3.9864. Min Range: -3.9864

Max Act: 3.5583. Min Act: -0.0000

Data Index: 875593 (The Pile)

Max Activating Token Index: 218

Text #8

Max Range: 3.9864. Min Range: -3.9864

Max Act: 3.4515. Min Act: -0.0000

Data Index: 975798 (The Pile)

Max Activating Token Index: 106

Text #9

Max Range: 3.9864. Min Range: -3.9864

Max Act: 3.4700. Min Act: -0.0000

Data Index: 111249 (The Pile)

Max Activating Token Index: 41

Text #10

Max Range: 3.9864. Min Range: -3.9864

Max Act: 3.0885. Min Act: -0.0000

Data Index: 1673226 (The Pile)

Max Activating Token Index: 143

Text #11

Max Range: 3.9864. Min Range: -3.9864

Max Act: 3.5839. Min Act: -0.0000

Data Index: 1652602 (The Pile)

Max Activating Token Index: 313

Text #12

Max Range: 3.9864. Min Range: -3.9864

Max Act: 3.4028. Min Act: -0.0000

Data Index: 100082 (The Pile)

Max Activating Token Index: 28

Text #13

Max Range: 3.9864. Min Range: -3.9864

Max Act: 3.1781. Min Act: 0.0000

Data Index: 235876 (The Pile)

Max Activating Token Index: 26

Text #14

Max Range: 3.9864. Min Range: -3.9864

Max Act: 3.1382. Min Act: -0.0000

Data Index: 1080539 (The Pile)

Max Activating Token Index: 87

Text #15

Max Range: 3.9864. Min Range: -3.9864

Max Act: 3.3903. Min Act: 0.0000

Data Index: 1970971 (The Pile)

Max Activating Token Index: 71

Text #16

Max Range: 3.9864. Min Range: -3.9864

Max Act: 3.0120. Min Act: -0.0000

Data Index: 883593 (The Pile)

Max Activating Token Index: 408

Text #17

Max Range: 3.9864. Min Range: -3.9864

Max Act: 2.9503. Min Act: -0.0000

Data Index: 1128963 (The Pile)

Max Activating Token Index: 787

Text #18

Max Range: 3.9864. Min Range: -3.9864

Max Act: 3.0957. Min Act: -0.0000

Data Index: 1244314 (The Pile)

Max Activating Token Index: 118

Text #19

Max Range: 3.9864. Min Range: -3.9864

Max Act: 3.1651. Min Act: -0.0000

Data Index: 347804 (The Pile)

Max Activating Token Index: 12