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

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

Neuron 3755 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.3922. Min Act: -0.0001

Data Index: 168847 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.3621. Min Act: -0.0001

Data Index: 1478483 (Python Code)

Max Activating Token Index: 999

Text #2

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.3205. Min Act: -0.0000

Data Index: 74362 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.3149. Min Act: -0.0001

Data Index: 485986 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.3026. Min Act: -0.0000

Data Index: 1350928 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.3116. Min Act: -0.0000

Data Index: 148949 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.3113. Min Act: -0.0001

Data Index: 1521339 (Python Code)

Max Activating Token Index: 479

Text #7

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2963. Min Act: -0.0001

Data Index: 1257877 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2972. Min Act: -0.0001

Data Index: 1162545 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2936. Min Act: -0.0001

Data Index: 1412188 (Python Code)

Max Activating Token Index: 732

Text #10

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.3030. Min Act: -0.0001

Data Index: 1491908 (Python Code)

Max Activating Token Index: 331

Text #11

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2987. Min Act: -0.0000

Data Index: 1059550 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2723. Min Act: -0.0001

Data Index: 1580449 (Python Code)

Max Activating Token Index: 567

Text #13

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2855. Min Act: -0.0000

Data Index: 848942 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2750. Min Act: -0.0000

Data Index: 271809 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2811. Min Act: -0.0000

Data Index: 726691 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2742. Min Act: -0.0000

Data Index: 848676 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1127516 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2759. Min Act: -0.0000

Data Index: 166763 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2729. Min Act: -0.0001

Data Index: 1291996 (C4 (Web Text))

Max Activating Token Index: 441