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

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

Neuron 1099 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.7722. Min Act: -0.0000

Data Index: 1592363 (Python Code)

Max Activating Token Index: 502

Text #1

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.7396. Min Act: 0.0001

Data Index: 1398064 (Python Code)

Max Activating Token Index: 486

Text #2

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.7721. Min Act: -0.0000

Data Index: 1364930 (Python Code)

Max Activating Token Index: 334

Text #3

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.6097. Min Act: -0.0000

Data Index: 1466502 (Python Code)

Max Activating Token Index: 235

Text #4

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.5117. Min Act: -0.0000

Data Index: 1500566 (Python Code)

Max Activating Token Index: 37

Text #5

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.5174. Min Act: -0.0000

Data Index: 1636156 (Python Code)

Max Activating Token Index: 80

Text #6

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.5556. Min Act: -0.0000

Data Index: 1603890 (Python Code)

Max Activating Token Index: 878

Text #7

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.5002. Min Act: 0.0000

Data Index: 1560661 (Python Code)

Max Activating Token Index: 198

Text #8

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.4403. Min Act: -0.0000

Data Index: 1636570 (Python Code)

Max Activating Token Index: 432

Text #9

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.4225. Min Act: -0.0000

Data Index: 1582756 (Python Code)

Max Activating Token Index: 179

Text #10

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.3676. Min Act: -0.0000

Data Index: 1608529 (Python Code)

Max Activating Token Index: 586

Text #11

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.4354. Min Act: -0.0000

Data Index: 1429680 (Python Code)

Max Activating Token Index: 693

Text #12

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.3480. Min Act: -0.0000

Data Index: 1425996 (Python Code)

Max Activating Token Index: 935

Text #13

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.3099. Min Act: -0.0000

Data Index: 1456242 (Python Code)

Max Activating Token Index: 608

Text #14

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.3319. Min Act: -0.0000

Data Index: 1623835 (Python Code)

Max Activating Token Index: 934

Text #15

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.2466. Min Act: -0.0000

Data Index: 1606315 (Python Code)

Max Activating Token Index: 34

Text #16

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.2413. Min Act: -0.0000

Data Index: 1527984 (Python Code)

Max Activating Token Index: 68

Text #17

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.2450. Min Act: -0.0000

Data Index: 1442866 (Python Code)

Max Activating Token Index: 816

Text #18

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.0975. Min Act: -0.0000

Data Index: 1609297 (Python Code)

Max Activating Token Index: 904

Text #19

Max Range: 1.7722. Min Range: -1.7722

Max Act: 1.2301. Min Act: -0.0000

Data Index: 1653832 (Python Code)

Max Activating Token Index: 514