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

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

Neuron 1472 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3635. Min Act: -0.0001

Data Index: 452611 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.4688. Min Act: -0.0001

Data Index: 336866 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.4544. Min Act: -0.0001

Data Index: 648591 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3430. Min Act: -0.0001

Data Index: 1317812 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.4103. Min Act: -0.0001

Data Index: 277371 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3804. Min Act: -0.0001

Data Index: 994168 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3855. Min Act: -0.0001

Data Index: 210305 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.4416. Min Act: -0.0001

Data Index: 363801 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3175. Min Act: -0.0001

Data Index: 880078 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3573. Min Act: -0.0001

Data Index: 960449 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3354. Min Act: -0.0001

Data Index: 227480 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3466. Min Act: -0.0001

Data Index: 1245824 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3197. Min Act: -0.0001

Data Index: 485125 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3902. Min Act: -0.0001

Data Index: 1351987 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3288. Min Act: -0.0001

Data Index: 1356027 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3491. Min Act: -0.0001

Data Index: 813314 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.2912. Min Act: -0.0001

Data Index: 418536 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3223. Min Act: -0.0001

Data Index: 824000 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3538. Min Act: -0.0001

Data Index: 265943 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3405. Min Act: -0.0001

Data Index: 1164264 (C4 (Web Text))

Max Activating Token Index: 716