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

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

Neuron 441 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: 1.0923. Min Range: -1.0923

Max Act: 1.0923. Min Act: -0.0000

Data Index: 1463142 (Python Code)

Max Activating Token Index: 102

Text #1

Max Range: 1.0923. Min Range: -1.0923

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1511856 (Python Code)

Max Activating Token Index: 436

Text #2

Max Range: 1.0923. Min Range: -1.0923

Max Act: 1.0171. Min Act: -0.0000

Data Index: 1646922 (Python Code)

Max Activating Token Index: 59

Text #3

Max Range: 1.0923. Min Range: -1.0923

Max Act: 1.0132. Min Act: -0.0000

Data Index: 1391107 (Python Code)

Max Activating Token Index: 995

Text #4

Max Range: 1.0923. Min Range: -1.0923

Max Act: 1.0593. Min Act: -0.0000

Data Index: 1651017 (Python Code)

Max Activating Token Index: 566

Text #5

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.9476. Min Act: -0.0000

Data Index: 1499991 (Python Code)

Max Activating Token Index: 419

Text #6

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8479. Min Act: -0.0000

Data Index: 1482687 (Python Code)

Max Activating Token Index: 524

Text #7

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8929. Min Act: -0.0000

Data Index: 304481 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.9614. Min Act: -0.0000

Data Index: 1502887 (Python Code)

Max Activating Token Index: 228

Text #9

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8758. Min Act: -0.0000

Data Index: 1563212 (Python Code)

Max Activating Token Index: 49

Text #10

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8696. Min Act: -0.0000

Data Index: 1475404 (Python Code)

Max Activating Token Index: 770

Text #11

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8650. Min Act: -0.0000

Data Index: 1583772 (Python Code)

Max Activating Token Index: 151

Text #12

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.7871. Min Act: -0.0000

Data Index: 1400957 (Python Code)

Max Activating Token Index: 137

Text #13

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8804. Min Act: -0.0000

Data Index: 1437370 (Python Code)

Max Activating Token Index: 130

Text #14

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1627565 (Python Code)

Max Activating Token Index: 300

Text #15

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8301. Min Act: -0.0000

Data Index: 1546058 (Python Code)

Max Activating Token Index: 349

Text #16

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8129. Min Act: -0.0000

Data Index: 1624174 (Python Code)

Max Activating Token Index: 723

Text #17

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8670. Min Act: -0.0000

Data Index: 1455270 (Python Code)

Max Activating Token Index: 535

Text #18

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8348. Min Act: -0.0000

Data Index: 1619249 (Python Code)

Max Activating Token Index: 393

Text #19

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8540. Min Act: -0.0000

Data Index: 1369923 (Python Code)

Max Activating Token Index: 240