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

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

Neuron 1219 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6683. Min Range: -4.6683

Max Act: 4.6683. Min Act: -0.0000

Data Index: 777245 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 4.6683. Min Range: -4.6683

Max Act: 4.4921. Min Act: -0.0000

Data Index: 129111 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 4.6683. Min Range: -4.6683

Max Act: 4.1856. Min Act: -0.0000

Data Index: 846249 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 4.6683. Min Range: -4.6683

Max Act: 3.8459. Min Act: -0.0000

Data Index: 366020 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 4.6683. Min Range: -4.6683

Max Act: 3.5942. Min Act: -0.0000

Data Index: 1150741 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 4.6683. Min Range: -4.6683

Max Act: 3.4813. Min Act: -0.0000

Data Index: 685 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 4.6683. Min Range: -4.6683

Max Act: 3.6814. Min Act: -0.0000

Data Index: 1352634 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 4.6683. Min Range: -4.6683

Max Act: 3.3821. Min Act: -0.0000

Data Index: 188810 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 4.6683. Min Range: -4.6683

Max Act: 3.0913. Min Act: -0.0000

Data Index: 382808 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 4.6683. Min Range: -4.6683

Max Act: 3.0200. Min Act: -0.0000

Data Index: 331891 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 4.6683. Min Range: -4.6683

Max Act: 3.0907. Min Act: -0.0000

Data Index: 816767 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 4.6683. Min Range: -4.6683

Max Act: 2.9062. Min Act: -0.0000

Data Index: 820187 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 4.6683. Min Range: -4.6683

Max Act: 3.1121. Min Act: -0.0000

Data Index: 753590 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 4.6683. Min Range: -4.6683

Max Act: 3.1863. Min Act: -0.0001

Data Index: 182784 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 4.6683. Min Range: -4.6683

Max Act: 2.9545. Min Act: -0.0000

Data Index: 1358461 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 4.6683. Min Range: -4.6683

Max Act: 2.4945. Min Act: -0.0000

Data Index: 996484 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 4.6683. Min Range: -4.6683

Max Act: 2.7346. Min Act: -0.0000

Data Index: 1038671 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 4.6683. Min Range: -4.6683

Max Act: 2.5478. Min Act: -0.0000

Data Index: 949868 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 4.6683. Min Range: -4.6683

Max Act: 2.5887. Min Act: -0.0000

Data Index: 484174 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 4.6683. Min Range: -4.6683

Max Act: 2.5536. Min Act: -0.0000

Data Index: 1295868 (C4 (Web Text))

Max Activating Token Index: 650