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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4786 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5744. Min Act: -0.0000

Data Index: 534124 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.5042. Min Act: -0.0000

Data Index: 489966 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4871. Min Act: -0.0000

Data Index: 216430 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1145304 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4666. Min Act: -0.0000

Data Index: 635762 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4269. Min Act: -0.0000

Data Index: 932922 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4430. Min Act: -0.0000

Data Index: 800015 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1340202 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4278. Min Act: -0.0000

Data Index: 88680 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4215. Min Act: -0.0000

Data Index: 293194 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1228182 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4143. Min Act: -0.0000

Data Index: 246 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4145. Min Act: -0.0000

Data Index: 690437 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1215245 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4046. Min Act: -0.0000

Data Index: 746928 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4039. Min Act: -0.0000

Data Index: 484587 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4045. Min Act: -0.0000

Data Index: 544799 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4024. Min Act: -0.0000

Data Index: 944236 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.3888. Min Act: -0.0000

Data Index: 590970 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.5744. Min Range: -0.5744

Max Act: 0.4104. Min Act: -0.0000

Data Index: 92700 (C4 (Web Text))

Max Activating Token Index: 649