Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1348 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0957. Min Act: -0.0003

Data Index: 324208 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0859. Min Act: -0.0004

Data Index: 699021 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0823. Min Act: -0.0003

Data Index: 1178479 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0813. Min Act: -0.0004

Data Index: 559499 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0866. Min Act: -0.0003

Data Index: 271631 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0826. Min Act: -0.0003

Data Index: 475279 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0852. Min Act: -0.0002

Data Index: 952303 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0800. Min Act: -0.0004

Data Index: 671957 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0804. Min Act: -0.0003

Data Index: 56374 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0785. Min Act: -0.0003

Data Index: 1103671 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0784. Min Act: -0.0003

Data Index: 456309 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0786. Min Act: -0.0003

Data Index: 754971 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0750. Min Act: -0.0003

Data Index: 607589 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0762. Min Act: -0.0002

Data Index: 161459 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0764. Min Act: -0.0003

Data Index: 1227447 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0764. Min Act: -0.0003

Data Index: 308084 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0739. Min Act: -0.0003

Data Index: 1146912 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0740. Min Act: -0.0003

Data Index: 907300 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0736. Min Act: -0.0003

Data Index: 90487 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0734. Min Act: -0.0004

Data Index: 263229 (C4 (Web Text))

Max Activating Token Index: 838