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

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

Neuron 2522 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0086. Min Range: -1.0086

Max Act: 1.0086. Min Act: -0.0000

Data Index: 402424 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.8796. Min Act: -0.0000

Data Index: 369286 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.8227. Min Act: -0.0000

Data Index: 933846 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7805. Min Act: -0.0000

Data Index: 80506 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7653. Min Act: -0.0000

Data Index: 958526 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.8140. Min Act: -0.0000

Data Index: 1208011 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.8017. Min Act: -0.0000

Data Index: 272163 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7573. Min Act: -0.0000

Data Index: 3945 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7465. Min Act: -0.0000

Data Index: 239164 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1066223 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7490. Min Act: -0.0000

Data Index: 1120082 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7892. Min Act: -0.0000

Data Index: 842117 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.8270. Min Act: -0.0000

Data Index: 362205 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1224780 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7305. Min Act: -0.0000

Data Index: 206456 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7740. Min Act: -0.0000

Data Index: 1266584 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.8219. Min Act: -0.0000

Data Index: 215301 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.7829. Min Act: -0.0000

Data Index: 996952 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1058341 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 1.0086. Min Range: -1.0086

Max Act: 0.6792. Min Act: -0.0000

Data Index: 1046163 (C4 (Web Text))

Max Activating Token Index: 302