Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 876 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1194. Min Act: -0.0002

Data Index: 486090 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1212. Min Act: -0.0002

Data Index: 998941 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1124. Min Act: -0.0002

Data Index: 446325 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1074. Min Act: -0.0002

Data Index: 579458 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1121. Min Act: -0.0002

Data Index: 1008530 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1067. Min Act: -0.0001

Data Index: 817255 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1019. Min Act: -0.0001

Data Index: 1282121 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1003. Min Act: -0.0001

Data Index: 861338 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1088. Min Act: -0.0002

Data Index: 264784 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1007. Min Act: -0.0002

Data Index: 332688 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1010. Min Act: -0.0002

Data Index: 869407 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1004. Min Act: -0.0001

Data Index: 568178 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0972. Min Act: -0.0001

Data Index: 520747 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0965. Min Act: -0.0002

Data Index: 127078 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0984. Min Act: -0.0002

Data Index: 232776 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0981. Min Act: -0.0002

Data Index: 914354 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0989. Min Act: -0.0002

Data Index: 508079 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0980. Min Act: -0.0002

Data Index: 461773 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0971. Min Act: -0.0002

Data Index: 590772 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1013. Min Act: -0.0002

Data Index: 1352008 (C4 (Web Text))

Max Activating Token Index: 270