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

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

Neuron 4753 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0079. Min Act: -0.0002

Data Index: 518679 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0075. Min Act: -0.0002

Data Index: 66348 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0073. Min Act: -0.0002

Data Index: 1337552 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0074. Min Act: -0.0002

Data Index: 394668 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0063. Min Act: -0.0002

Data Index: 649369 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0065. Min Act: -0.0002

Data Index: 554467 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0063. Min Act: -0.0002

Data Index: 91315 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0063. Min Act: -0.0002

Data Index: 443435 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0062. Min Act: -0.0002

Data Index: 742986 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0064. Min Act: -0.0002

Data Index: 1151367 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0058. Min Act: -0.0002

Data Index: 166953 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0059. Min Act: -0.0002

Data Index: 686889 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0056. Min Act: -0.0002

Data Index: 799222 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0058. Min Act: -0.0002

Data Index: 995333 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0060. Min Act: -0.0002

Data Index: 152502 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0057. Min Act: -0.0002

Data Index: 463471 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0056. Min Act: -0.0002

Data Index: 47703 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1274634 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1264688 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0056. Min Act: -0.0002

Data Index: 573985 (C4 (Web Text))

Max Activating Token Index: 652