Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3182 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.5603. Min Act: -0.0000

Data Index: 259498 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.5013. Min Act: 0.0000

Data Index: 666350 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1143415 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1215465 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3504. Min Act: -0.0000

Data Index: 1121277 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3536. Min Act: -0.0000

Data Index: 543945 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3644. Min Act: -0.0000

Data Index: 1193242 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3329. Min Act: -0.0000

Data Index: 395457 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3281. Min Act: -0.0000

Data Index: 269660 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3157. Min Act: -0.0000

Data Index: 440767 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3035. Min Act: -0.0000

Data Index: 1171596 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.2930. Min Act: -0.0000

Data Index: 765330 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1159269 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.3030. Min Act: -0.0000

Data Index: 1184273 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.2992. Min Act: -0.0000

Data Index: 109384 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.2638. Min Act: -0.0000

Data Index: 1357890 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.2890. Min Act: -0.0000

Data Index: 22774 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.2787. Min Act: -0.0000

Data Index: 36131 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.2699. Min Act: -0.0000

Data Index: 918013 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.5603. Min Range: -0.5603

Max Act: 0.2824. Min Act: 0.0000

Data Index: 24039 (C4 (Web Text))

Max Activating Token Index: 977