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

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

Neuron 1790 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: 2.7491. Min Range: -2.7491

Max Act: 2.7491. Min Act: -0.0000

Data Index: 136423 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 2.7491. Min Range: -2.7491

Max Act: 2.4657. Min Act: -0.0000

Data Index: 914982 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 2.7491. Min Range: -2.7491

Max Act: 2.7080. Min Act: -0.0000

Data Index: 1358551 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 2.7491. Min Range: -2.7491

Max Act: 2.2712. Min Act: -0.0000

Data Index: 1106158 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 2.7491. Min Range: -2.7491

Max Act: 2.2396. Min Act: -0.0000

Data Index: 1542068 (Python Code)

Max Activating Token Index: 805

Text #5

Max Range: 2.7491. Min Range: -2.7491

Max Act: 2.2409. Min Act: -0.0000

Data Index: 245913 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 2.7491. Min Range: -2.7491

Max Act: 2.0547. Min Act: -0.0000

Data Index: 1069407 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 2.7491. Min Range: -2.7491

Max Act: 2.1771. Min Act: -0.0000

Data Index: 1186925 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 2.7491. Min Range: -2.7491

Max Act: 2.1699. Min Act: -0.0000

Data Index: 1485194 (Python Code)

Max Activating Token Index: 68

Text #9

Max Range: 2.7491. Min Range: -2.7491

Max Act: 2.1086. Min Act: -0.0000

Data Index: 164798 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 2.7491. Min Range: -2.7491

Max Act: 2.1072. Min Act: -0.0000

Data Index: 942085 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 2.7491. Min Range: -2.7491

Max Act: 2.0865. Min Act: -0.0000

Data Index: 160997 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 2.7491. Min Range: -2.7491

Max Act: 1.9566. Min Act: -0.0000

Data Index: 1355654 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 2.7491. Min Range: -2.7491

Max Act: 1.9676. Min Act: -0.0000

Data Index: 438896 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 2.7491. Min Range: -2.7491

Max Act: 2.0671. Min Act: -0.0000

Data Index: 1089404 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 2.7491. Min Range: -2.7491

Max Act: 2.0774. Min Act: -0.0000

Data Index: 1206072 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 2.7491. Min Range: -2.7491

Max Act: 2.0617. Min Act: -0.0000

Data Index: 1020378 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 2.7491. Min Range: -2.7491

Max Act: 2.1360. Min Act: -0.0000

Data Index: 95320 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 2.7491. Min Range: -2.7491

Max Act: 2.0069. Min Act: -0.0000

Data Index: 315612 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 2.7491. Min Range: -2.7491

Max Act: 1.9986. Min Act: -0.0000

Data Index: 382816 (C4 (Web Text))

Max Activating Token Index: 385