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

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

Neuron 977 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.6591. Min Act: -0.0001

Data Index: 616916 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5648. Min Act: -0.0001

Data Index: 694168 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5421. Min Act: -0.0001

Data Index: 96892 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5499. Min Act: -0.0001

Data Index: 787765 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5469. Min Act: -0.0001

Data Index: 1233922 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5435. Min Act: -0.0001

Data Index: 922457 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4994. Min Act: -0.0001

Data Index: 696688 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4568. Min Act: -0.0001

Data Index: 108650 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5010. Min Act: -0.0001

Data Index: 632648 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4883. Min Act: -0.0001

Data Index: 675804 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4930. Min Act: -0.0001

Data Index: 321827 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4850. Min Act: -0.0001

Data Index: 576532 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4184. Min Act: -0.0001

Data Index: 1192131 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4689. Min Act: -0.0001

Data Index: 120227 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4468. Min Act: -0.0001

Data Index: 1190219 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4725. Min Act: -0.0001

Data Index: 37989 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4461. Min Act: -0.0001

Data Index: 305938 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4391. Min Act: -0.0001

Data Index: 314187 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4833. Min Act: -0.0001

Data Index: 304125 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4779. Min Act: -0.0001

Data Index: 789916 (C4 (Web Text))

Max Activating Token Index: 736