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

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

Neuron 3672 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6120. Min Range: -1.6120

Max Act: 1.6120. Min Act: -0.0000

Data Index: 512963 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 1.6120. Min Range: -1.6120

Max Act: 0.9863. Min Act: -0.0000

Data Index: 1044297 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 1.6120. Min Range: -1.6120

Max Act: 0.8918. Min Act: -0.0000

Data Index: 887370 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 1.6120. Min Range: -1.6120

Max Act: 0.8755. Min Act: -0.0000

Data Index: 234520 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 1.6120. Min Range: -1.6120

Max Act: 0.9354. Min Act: -0.0000

Data Index: 524600 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 1.6120. Min Range: -1.6120

Max Act: 0.8674. Min Act: -0.0000

Data Index: 476237 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 1.6120. Min Range: -1.6120

Max Act: 0.8825. Min Act: -0.0000

Data Index: 1130928 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 1.6120. Min Range: -1.6120

Max Act: 0.7878. Min Act: -0.0000

Data Index: 317891 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 1.6120. Min Range: -1.6120

Max Act: 0.7447. Min Act: -0.0000

Data Index: 211854 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 1.6120. Min Range: -1.6120

Max Act: 0.7880. Min Act: -0.0000

Data Index: 889986 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 1.6120. Min Range: -1.6120

Max Act: 0.7827. Min Act: -0.0000

Data Index: 637942 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 1.6120. Min Range: -1.6120

Max Act: 0.8257. Min Act: -0.0000

Data Index: 299438 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 1.6120. Min Range: -1.6120

Max Act: 0.7684. Min Act: -0.0000

Data Index: 321885 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 1.6120. Min Range: -1.6120

Max Act: 0.7482. Min Act: -0.0000

Data Index: 1253149 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 1.6120. Min Range: -1.6120

Max Act: 0.7157. Min Act: -0.0000

Data Index: 1159766 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 1.6120. Min Range: -1.6120

Max Act: 0.7335. Min Act: -0.0000

Data Index: 624739 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 1.6120. Min Range: -1.6120

Max Act: 0.7891. Min Act: -0.0000

Data Index: 301732 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 1.6120. Min Range: -1.6120

Max Act: 0.7029. Min Act: -0.0000

Data Index: 304131 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 1.6120. Min Range: -1.6120

Max Act: 0.7073. Min Act: -0.0000

Data Index: 891091 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 1.6120. Min Range: -1.6120

Max Act: 0.6900. Min Act: -0.0000

Data Index: 961571 (C4 (Web Text))

Max Activating Token Index: 121