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

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

Neuron 3918 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0542. Min Act: -0.0002

Data Index: 323890 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0555. Min Act: -0.0002

Data Index: 177449 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1086187 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0548. Min Act: -0.0002

Data Index: 772585 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1162474 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0541. Min Act: -0.0002

Data Index: 27038 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1038343 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0537. Min Act: -0.0002

Data Index: 211177 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1133415 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0556. Min Act: -0.0002

Data Index: 933259 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0533. Min Act: -0.0002

Data Index: 205438 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0524. Min Act: -0.0002

Data Index: 1191425 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0515. Min Act: -0.0002

Data Index: 510152 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0511. Min Act: -0.0002

Data Index: 910224 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0506. Min Act: -0.0002

Data Index: 1008731 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1356997 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1208552 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0493. Min Act: -0.0002

Data Index: 734868 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0492. Min Act: -0.0002

Data Index: 272453 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0489. Min Act: -0.0002

Data Index: 923988 (C4 (Web Text))

Max Activating Token Index: 38