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

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

Neuron 458 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.9504. Min Act: -0.0000

Data Index: 1607423 (Python Code)

Max Activating Token Index: 116

Text #1

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.8674. Min Act: -0.0000

Data Index: 763338 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7756. Min Act: -0.0000

Data Index: 704381 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.8197. Min Act: -0.0000

Data Index: 93648 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.8218. Min Act: -0.0000

Data Index: 1197484 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7800. Min Act: -0.0000

Data Index: 131873 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7398. Min Act: -0.0000

Data Index: 272122 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7245. Min Act: -0.0000

Data Index: 236666 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7684. Min Act: -0.0000

Data Index: 581334 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1330407 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7844. Min Act: -0.0000

Data Index: 584819 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6718. Min Act: -0.0000

Data Index: 1122656 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7305. Min Act: -0.0000

Data Index: 1290569 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7125. Min Act: -0.0000

Data Index: 1134769 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7360. Min Act: -0.0000

Data Index: 803202 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6902. Min Act: -0.0000

Data Index: 1185134 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7134. Min Act: -0.0000

Data Index: 126340 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7366. Min Act: -0.0000

Data Index: 1078684 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7151. Min Act: -0.0000

Data Index: 393681 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6596. Min Act: -0.0000

Data Index: 799228 (C4 (Web Text))

Max Activating Token Index: 321