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

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

Neuron 2060 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.9204. Min Act: -0.0000

Data Index: 1508976 (Python Code)

Max Activating Token Index: 867

Text #1

Max Range: 2.0651. Min Range: -2.0651

Max Act: 2.0651. Min Act: -0.0000

Data Index: 1438645 (Python Code)

Max Activating Token Index: 1016

Text #2

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.9364. Min Act: -0.0000

Data Index: 1509100 (Python Code)

Max Activating Token Index: 318

Text #3

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.8715. Min Act: -0.0000

Data Index: 1414223 (Python Code)

Max Activating Token Index: 992

Text #4

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.8482. Min Act: -0.0000

Data Index: 1497171 (Python Code)

Max Activating Token Index: 665

Text #5

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.7368. Min Act: -0.0000

Data Index: 1505115 (Python Code)

Max Activating Token Index: 47

Text #6

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.7771. Min Act: -0.0001

Data Index: 1570824 (Python Code)

Max Activating Token Index: 458

Text #7

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.6425. Min Act: -0.0000

Data Index: 1508915 (Python Code)

Max Activating Token Index: 302

Text #8

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.7255. Min Act: -0.0000

Data Index: 1546543 (Python Code)

Max Activating Token Index: 127

Text #9

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.6199. Min Act: -0.0000

Data Index: 1389812 (Python Code)

Max Activating Token Index: 24

Text #10

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.8122. Min Act: -0.0000

Data Index: 1521035 (Python Code)

Max Activating Token Index: 678

Text #11

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.8083. Min Act: -0.0000

Data Index: 1462733 (Python Code)

Max Activating Token Index: 508

Text #12

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.8636. Min Act: -0.0000

Data Index: 1418486 (Python Code)

Max Activating Token Index: 387

Text #13

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.7910. Min Act: -0.0000

Data Index: 1564176 (Python Code)

Max Activating Token Index: 46

Text #14

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.6258. Min Act: -0.0000

Data Index: 1562052 (Python Code)

Max Activating Token Index: 698

Text #15

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.6289. Min Act: -0.0000

Data Index: 1449981 (Python Code)

Max Activating Token Index: 89

Text #16

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.6307. Min Act: -0.0000

Data Index: 1654125 (Python Code)

Max Activating Token Index: 373

Text #17

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.4534. Min Act: -0.0000

Data Index: 1492666 (Python Code)

Max Activating Token Index: 859

Text #18

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.6998. Min Act: -0.0000

Data Index: 1411595 (Python Code)

Max Activating Token Index: 1019

Text #19

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.6536. Min Act: -0.0001

Data Index: 1451480 (Python Code)

Max Activating Token Index: 21