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

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

Neuron 4855 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1428. Min Act: -0.0002

Data Index: 677508 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1204. Min Act: -0.0002

Data Index: 519741 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1161. Min Act: -0.0002

Data Index: 82413 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1018. Min Act: -0.0002

Data Index: 94134 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1106. Min Act: -0.0002

Data Index: 37817 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1039. Min Act: -0.0002

Data Index: 561981 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1055. Min Act: -0.0002

Data Index: 750351 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0946. Min Act: -0.0002

Data Index: 204165 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1003. Min Act: -0.0002

Data Index: 1261750 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0929. Min Act: -0.0002

Data Index: 691781 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0965. Min Act: -0.0002

Data Index: 618174 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0965. Min Act: -0.0002

Data Index: 1002521 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0864. Min Act: -0.0002

Data Index: 687095 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0955. Min Act: -0.0002

Data Index: 7813 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0877. Min Act: -0.0002

Data Index: 452913 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0894. Min Act: -0.0002

Data Index: 120361 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0963. Min Act: -0.0002

Data Index: 794938 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0885. Min Act: -0.0002

Data Index: 785994 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1009. Min Act: -0.0002

Data Index: 1172654 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0949. Min Act: -0.0002

Data Index: 1179849 (C4 (Web Text))

Max Activating Token Index: 251