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

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

Neuron 229 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1499. Min Range: -2.1499

Max Act: 2.1499. Min Act: -0.0000

Data Index: 866766 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 2.1499. Min Range: -2.1499

Max Act: 2.0433. Min Act: -0.0000

Data Index: 1110137 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 2.1499. Min Range: -2.1499

Max Act: 2.0231. Min Act: -0.0000

Data Index: 1480395 (Python Code)

Max Activating Token Index: 688

Text #3

Max Range: 2.1499. Min Range: -2.1499

Max Act: 1.9340. Min Act: -0.0000

Data Index: 1454985 (Python Code)

Max Activating Token Index: 380

Text #4

Max Range: 2.1499. Min Range: -2.1499

Max Act: 1.8801. Min Act: -0.0000

Data Index: 1539349 (Python Code)

Max Activating Token Index: 99

Text #5

Max Range: 2.1499. Min Range: -2.1499

Max Act: 1.7194. Min Act: -0.0000

Data Index: 1242163 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 2.1499. Min Range: -2.1499

Max Act: 1.6303. Min Act: -0.0000

Data Index: 1388164 (Python Code)

Max Activating Token Index: 592

Text #7

Max Range: 2.1499. Min Range: -2.1499

Max Act: 1.6937. Min Act: -0.0000

Data Index: 1425831 (Python Code)

Max Activating Token Index: 502

Text #8

Max Range: 2.1499. Min Range: -2.1499

Max Act: 1.7544. Min Act: -0.0000

Data Index: 1459857 (Python Code)

Max Activating Token Index: 562

Text #9

Max Range: 2.1499. Min Range: -2.1499

Max Act: 1.6584. Min Act: -0.0000

Data Index: 1366227 (Python Code)

Max Activating Token Index: 987

Text #10

Max Range: 2.1499. Min Range: -2.1499

Max Act: 1.5611. Min Act: -0.0000

Data Index: 1479110 (Python Code)

Max Activating Token Index: 400

Text #11

Max Range: 2.1499. Min Range: -2.1499

Max Act: 1.6192. Min Act: -0.0000

Data Index: 1523264 (Python Code)

Max Activating Token Index: 729

Text #12

Max Range: 2.1499. Min Range: -2.1499

Max Act: 1.5819. Min Act: -0.0000

Data Index: 1537367 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 2.1499. Min Range: -2.1499

Max Act: 1.5781. Min Act: -0.0000

Data Index: 165768 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 2.1499. Min Range: -2.1499

Max Act: 1.4763. Min Act: -0.0000

Data Index: 1507730 (Python Code)

Max Activating Token Index: 669

Text #15

Max Range: 2.1499. Min Range: -2.1499

Max Act: 1.5503. Min Act: -0.0000

Data Index: 1559622 (Python Code)

Max Activating Token Index: 564

Text #16

Max Range: 2.1499. Min Range: -2.1499

Max Act: 1.6229. Min Act: -0.0000

Data Index: 1600961 (Python Code)

Max Activating Token Index: 307

Text #17

Max Range: 2.1499. Min Range: -2.1499

Max Act: 1.5321. Min Act: -0.0000

Data Index: 1414280 (Python Code)

Max Activating Token Index: 650

Text #18

Max Range: 2.1499. Min Range: -2.1499

Max Act: 1.5809. Min Act: -0.0000

Data Index: 1440654 (Python Code)

Max Activating Token Index: 516

Text #19

Max Range: 2.1499. Min Range: -2.1499

Max Act: 1.4201. Min Act: -0.0000

Data Index: 293115 (C4 (Web Text))

Max Activating Token Index: 1020