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

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

Neuron 3464 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.6615. Min Act: -0.0000

Data Index: 1494609 (Python Code)

Max Activating Token Index: 480

Text #1

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.7524. Min Act: -0.0001

Data Index: 1648654 (Python Code)

Max Activating Token Index: 317

Text #2

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.6662. Min Act: -0.0000

Data Index: 1515055 (Python Code)

Max Activating Token Index: 97

Text #3

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.7484. Min Act: -0.0000

Data Index: 1388349 (Python Code)

Max Activating Token Index: 124

Text #4

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.5887. Min Act: -0.0000

Data Index: 1542327 (Python Code)

Max Activating Token Index: 257

Text #5

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.3985. Min Act: -0.0000

Data Index: 1434280 (Python Code)

Max Activating Token Index: 138

Text #6

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.3634. Min Act: -0.0000

Data Index: 1445105 (Python Code)

Max Activating Token Index: 864

Text #7

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.3283. Min Act: -0.0001

Data Index: 1648485 (Python Code)

Max Activating Token Index: 289

Text #8

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.3616. Min Act: -0.0000

Data Index: 1635765 (Python Code)

Max Activating Token Index: 138

Text #9

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.3767. Min Act: -0.0000

Data Index: 1534969 (Python Code)

Max Activating Token Index: 25

Text #10

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.2787. Min Act: -0.0000

Data Index: 1363455 (Python Code)

Max Activating Token Index: 51

Text #11

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.3453. Min Act: -0.0000

Data Index: 1578988 (Python Code)

Max Activating Token Index: 66

Text #12

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.3045. Min Act: -0.0000

Data Index: 1420314 (Python Code)

Max Activating Token Index: 38

Text #13

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.2966. Min Act: -0.0000

Data Index: 1438813 (Python Code)

Max Activating Token Index: 337

Text #14

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.3891. Min Act: -0.0000

Data Index: 1627153 (Python Code)

Max Activating Token Index: 96

Text #15

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.2703. Min Act: -0.0000

Data Index: 1650859 (Python Code)

Max Activating Token Index: 16

Text #16

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.2624. Min Act: -0.0001

Data Index: 1542130 (Python Code)

Max Activating Token Index: 127

Text #17

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.3013. Min Act: -0.0000

Data Index: 1598435 (Python Code)

Max Activating Token Index: 80

Text #18

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.2970. Min Act: -0.0000

Data Index: 1625997 (Python Code)

Max Activating Token Index: 52

Text #19

Max Range: 1.7524. Min Range: -1.7524

Max Act: 1.3402. Min Act: -0.0000

Data Index: 1550904 (Python Code)

Max Activating Token Index: 131