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

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

Neuron 222 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: 0.1023. Min Range: -0.1023

Max Act: 0.1023. Min Act: -0.0002

Data Index: 1248127 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.1010. Min Act: -0.0002

Data Index: 890794 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0893. Min Act: -0.0002

Data Index: 233089 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0917. Min Act: -0.0002

Data Index: 832211 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0913. Min Act: -0.0002

Data Index: 524458 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0789. Min Act: -0.0002

Data Index: 1025964 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0798. Min Act: -0.0002

Data Index: 232732 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1169846 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0685. Min Act: -0.0002

Data Index: 1152205 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0747. Min Act: -0.0002

Data Index: 174999 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0727. Min Act: -0.0002

Data Index: 1240115 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0711. Min Act: -0.0002

Data Index: 139328 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1154668 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1212472 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1206899 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0649. Min Act: -0.0002

Data Index: 819431 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0629. Min Act: -0.0002

Data Index: 72443 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0595. Min Act: -0.0002

Data Index: 473286 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0649. Min Act: -0.0002

Data Index: 396940 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0680. Min Act: -0.0002

Data Index: 576883 (C4 (Web Text))

Max Activating Token Index: 1018