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

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

Neuron 5040 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1782. Min Act: -0.0002

Data Index: 679124 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1709. Min Act: -0.0002

Data Index: 865052 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1632. Min Act: -0.0003

Data Index: 1343145 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1638. Min Act: -0.0003

Data Index: 186650 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1560. Min Act: -0.0003

Data Index: 247367 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1716. Min Act: -0.0003

Data Index: 976270 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1450. Min Act: -0.0003

Data Index: 958482 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1498. Min Act: -0.0003

Data Index: 329907 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1530. Min Act: -0.0003

Data Index: 713223 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1477. Min Act: -0.0003

Data Index: 1179308 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1470. Min Act: -0.0002

Data Index: 480448 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1451. Min Act: -0.0003

Data Index: 614630 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1390. Min Act: -0.0003

Data Index: 618639 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1467. Min Act: -0.0002

Data Index: 727592 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1396. Min Act: -0.0003

Data Index: 249542 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1316. Min Act: -0.0003

Data Index: 1122332 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1404. Min Act: -0.0003

Data Index: 122219 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1440. Min Act: -0.0003

Data Index: 480165 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1347. Min Act: -0.0002

Data Index: 231387 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1385. Min Act: -0.0003

Data Index: 39770 (C4 (Web Text))

Max Activating Token Index: 979