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

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

Neuron 3187 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: 0.6090. Min Range: -0.6090

Max Act: 0.6090. Min Act: -0.0000

Data Index: 1475205 (Python Code)

Max Activating Token Index: 52

Text #1

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1366245 (Python Code)

Max Activating Token Index: 546

Text #2

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1621367 (Python Code)

Max Activating Token Index: 671

Text #3

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1545330 (Python Code)

Max Activating Token Index: 650

Text #4

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5227. Min Act: -0.0000

Data Index: 1494586 (Python Code)

Max Activating Token Index: 899

Text #5

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5346. Min Act: -0.0000

Data Index: 1422057 (Python Code)

Max Activating Token Index: 119

Text #6

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1541906 (Python Code)

Max Activating Token Index: 595

Text #7

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1370397 (Python Code)

Max Activating Token Index: 303

Text #8

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.4829. Min Act: -0.0000

Data Index: 1562464 (Python Code)

Max Activating Token Index: 536

Text #9

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1524145 (Python Code)

Max Activating Token Index: 941

Text #10

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1480504 (Python Code)

Max Activating Token Index: 884

Text #11

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.4800. Min Act: -0.0000

Data Index: 1636567 (Python Code)

Max Activating Token Index: 532

Text #12

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1458782 (Python Code)

Max Activating Token Index: 258

Text #13

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1561563 (Python Code)

Max Activating Token Index: 104

Text #14

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1547102 (Python Code)

Max Activating Token Index: 63

Text #15

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.4803. Min Act: -0.0000

Data Index: 1493537 (Python Code)

Max Activating Token Index: 376

Text #16

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.4853. Min Act: -0.0000

Data Index: 1360344 (Python Code)

Max Activating Token Index: 918

Text #17

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1592873 (Python Code)

Max Activating Token Index: 844

Text #18

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.4722. Min Act: -0.0000

Data Index: 1568491 (Python Code)

Max Activating Token Index: 219

Text #19

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.4711. Min Act: -0.0000

Data Index: 1503842 (Python Code)

Max Activating Token Index: 716