Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 688 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.9273. Min Act: -0.0001

Data Index: 1473500 (Python Code)

Max Activating Token Index: 62

Text #1

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.1956. Min Act: -0.0001

Data Index: 1374654 (Python Code)

Max Activating Token Index: 39

Text #2

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.1381. Min Act: -0.0001

Data Index: 1640354 (Python Code)

Max Activating Token Index: 111

Text #3

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.0915. Min Act: -0.0001

Data Index: 1406334 (Python Code)

Max Activating Token Index: 123

Text #4

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.1388. Min Act: -0.0001

Data Index: 1563580 (Python Code)

Max Activating Token Index: 100

Text #5

Max Range: 1.9273. Min Range: -1.9273

Max Act: 0.9497. Min Act: -0.0001

Data Index: 1389337 (Python Code)

Max Activating Token Index: 34

Text #6

Max Range: 1.9273. Min Range: -1.9273

Max Act: 1.0097. Min Act: -0.0001

Data Index: 1578156 (Python Code)

Max Activating Token Index: 119

Text #7

Max Range: 1.9273. Min Range: -1.9273

Max Act: 0.9489. Min Act: -0.0001

Data Index: 1604244 (Python Code)

Max Activating Token Index: 47

Text #8

Max Range: 1.9273. Min Range: -1.9273

Max Act: 0.9279. Min Act: -0.0001

Data Index: 1595817 (Python Code)

Max Activating Token Index: 132

Text #9

Max Range: 1.9273. Min Range: -1.9273

Max Act: 0.9264. Min Act: -0.0001

Data Index: 1611761 (Python Code)

Max Activating Token Index: 363

Text #10

Max Range: 1.9273. Min Range: -1.9273

Max Act: 0.8865. Min Act: -0.0001

Data Index: 1418282 (Python Code)

Max Activating Token Index: 54

Text #11

Max Range: 1.9273. Min Range: -1.9273

Max Act: 0.8322. Min Act: -0.0001

Data Index: 1431802 (Python Code)

Max Activating Token Index: 32

Text #12

Max Range: 1.9273. Min Range: -1.9273

Max Act: 0.8735. Min Act: -0.0001

Data Index: 1607645 (Python Code)

Max Activating Token Index: 912

Text #13

Max Range: 1.9273. Min Range: -1.9273

Max Act: 0.8198. Min Act: -0.0001

Data Index: 1453184 (Python Code)

Max Activating Token Index: 623

Text #14

Max Range: 1.9273. Min Range: -1.9273

Max Act: 0.7797. Min Act: -0.0001

Data Index: 1410489 (Python Code)

Max Activating Token Index: 610

Text #15

Max Range: 1.9273. Min Range: -1.9273

Max Act: 0.7790. Min Act: -0.0001

Data Index: 1609253 (Python Code)

Max Activating Token Index: 937

Text #16

Max Range: 1.9273. Min Range: -1.9273

Max Act: 0.8216. Min Act: -0.0001

Data Index: 1434775 (Python Code)

Max Activating Token Index: 334

Text #17

Max Range: 1.9273. Min Range: -1.9273

Max Act: 0.7948. Min Act: -0.0001

Data Index: 1616676 (Python Code)

Max Activating Token Index: 596

Text #18

Max Range: 1.9273. Min Range: -1.9273

Max Act: 0.7927. Min Act: -0.0001

Data Index: 1447453 (Python Code)

Max Activating Token Index: 152

Text #19

Max Range: 1.9273. Min Range: -1.9273

Max Act: 0.7902. Min Act: -0.0001

Data Index: 1635857 (Python Code)

Max Activating Token Index: 83