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

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

Neuron 5068 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.7581. Min Act: -0.0000

Data Index: 636719 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6932. Min Act: -0.0000

Data Index: 990979 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6496. Min Act: -0.0000

Data Index: 1277265 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6836. Min Act: -0.0000

Data Index: 627074 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6874. Min Act: -0.0000

Data Index: 439252 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.5932. Min Act: -0.0000

Data Index: 369299 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1149280 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6586. Min Act: -0.0000

Data Index: 58654 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.5727. Min Act: -0.0000

Data Index: 712915 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6427. Min Act: -0.0000

Data Index: 40414 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6162. Min Act: -0.0000

Data Index: 554403 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1315927 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6248. Min Act: -0.0000

Data Index: 339653 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.5866. Min Act: -0.0000

Data Index: 949919 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.5860. Min Act: -0.0000

Data Index: 836753 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1118723 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.5025. Min Act: -0.0000

Data Index: 385118 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.5512. Min Act: -0.0000

Data Index: 591195 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.5316. Min Act: -0.0000

Data Index: 645329 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.5633. Min Act: -0.0000

Data Index: 350852 (C4 (Web Text))

Max Activating Token Index: 990