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

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

Neuron 2704 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2340. Min Act: -0.0000

Data Index: 665664 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1997. Min Act: -0.0000

Data Index: 1065804 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2001. Min Act: -0.0000

Data Index: 746981 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1899. Min Act: -0.0000

Data Index: 601804 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1893. Min Act: -0.0000

Data Index: 429079 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1259715 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1784. Min Act: -0.0000

Data Index: 1127432 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1640. Min Act: -0.0000

Data Index: 620574 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1814. Min Act: -0.0000

Data Index: 1158992 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1655. Min Act: -0.0000

Data Index: 337397 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1663. Min Act: -0.0000

Data Index: 265194 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1593. Min Act: -0.0000

Data Index: 1259782 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1630. Min Act: -0.0000

Data Index: 435214 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1511. Min Act: -0.0000

Data Index: 504257 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1592. Min Act: -0.0000

Data Index: 12167 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1125944 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1489. Min Act: -0.0000

Data Index: 671756 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1615. Min Act: -0.0000

Data Index: 1093067 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1575. Min Act: -0.0000

Data Index: 217263 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1428. Min Act: -0.0000

Data Index: 1299512 (C4 (Web Text))

Max Activating Token Index: 339