Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2426 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0935. Min Act: -0.0001

Data Index: 750034 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0904. Min Act: -0.0001

Data Index: 501887 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1025956 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0893. Min Act: -0.0001

Data Index: 769472 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0894. Min Act: -0.0002

Data Index: 347261 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0773. Min Act: -0.0002

Data Index: 837005 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0882. Min Act: -0.0001

Data Index: 366454 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0843. Min Act: -0.0002

Data Index: 589968 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0906. Min Act: -0.0001

Data Index: 627584 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0744. Min Act: -0.0002

Data Index: 23544 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0910. Min Act: -0.0001

Data Index: 1374927 (Python Code)

Max Activating Token Index: 282

Text #11

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0845. Min Act: -0.0002

Data Index: 113108 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0815. Min Act: -0.0002

Data Index: 441296 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0704. Min Act: -0.0002

Data Index: 38492 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0776. Min Act: -0.0002

Data Index: 856897 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0788. Min Act: -0.0001

Data Index: 665423 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0785. Min Act: -0.0001

Data Index: 400544 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0764. Min Act: -0.0002

Data Index: 554203 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1371202 (Python Code)

Max Activating Token Index: 152

Text #19

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0798. Min Act: -0.0001

Data Index: 1506714 (Python Code)

Max Activating Token Index: 396