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

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

Neuron 2808 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: 0.7924. Min Range: -0.7924

Max Act: 0.7924. Min Act: -0.0000

Data Index: 1090260 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.6978. Min Act: -0.0000

Data Index: 500062 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.6777. Min Act: -0.0000

Data Index: 215512 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.6045. Min Act: -0.0000

Data Index: 971374 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.6060. Min Act: -0.0000

Data Index: 704213 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1086432 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.5112. Min Act: -0.0000

Data Index: 678992 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.5167. Min Act: -0.0000

Data Index: 189355 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.4831. Min Act: -0.0000

Data Index: 907900 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.5062. Min Act: -0.0000

Data Index: 283574 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.4550. Min Act: -0.0000

Data Index: 410189 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.4851. Min Act: -0.0000

Data Index: 122691 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.4827. Min Act: -0.0000

Data Index: 153732 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1112967 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.4800. Min Act: -0.0000

Data Index: 1094096 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.4675. Min Act: -0.0000

Data Index: 150678 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.4449. Min Act: -0.0000

Data Index: 224866 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.4712. Min Act: -0.0000

Data Index: 434094 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.4616. Min Act: -0.0000

Data Index: 733422 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.7924. Min Range: -0.7924

Max Act: 0.4598. Min Act: -0.0000

Data Index: 1067173 (C4 (Web Text))

Max Activating Token Index: 333