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

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

Neuron 3275 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.9581. Min Act: -0.0000

Data Index: 78961 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7914. Min Act: -0.0000

Data Index: 1286601 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7752. Min Act: -0.0000

Data Index: 798167 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1045219 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.8146. Min Act: -0.0000

Data Index: 1634869 (Python Code)

Max Activating Token Index: 900

Text #5

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7973. Min Act: -0.0000

Data Index: 379375 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.8179. Min Act: -0.0000

Data Index: 1498347 (Python Code)

Max Activating Token Index: 991

Text #7

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7869. Min Act: -0.0000

Data Index: 701663 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7133. Min Act: -0.0000

Data Index: 871855 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7441. Min Act: -0.0000

Data Index: 1194660 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7240. Min Act: -0.0000

Data Index: 567737 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7933. Min Act: -0.0000

Data Index: 433727 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7850. Min Act: -0.0000

Data Index: 275987 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1236115 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7359. Min Act: -0.0000

Data Index: 408421 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1470198 (Python Code)

Max Activating Token Index: 821

Text #16

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7494. Min Act: -0.0000

Data Index: 327921 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7782. Min Act: -0.0000

Data Index: 139552 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7076. Min Act: -0.0000

Data Index: 261229 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7075. Min Act: -0.0000

Data Index: 249335 (C4 (Web Text))

Max Activating Token Index: 896