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

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

Neuron 4227 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6589. Min Range: -2.6589

Max Act: 2.5857. Min Act: -0.0000

Data Index: 1368953 (Python Code)

Max Activating Token Index: 383

Text #1

Max Range: 2.6589. Min Range: -2.6589

Max Act: 2.5660. Min Act: -0.0000

Data Index: 1582631 (Python Code)

Max Activating Token Index: 869

Text #2

Max Range: 2.6589. Min Range: -2.6589

Max Act: 2.6589. Min Act: -0.0000

Data Index: 1460219 (Python Code)

Max Activating Token Index: 204

Text #3

Max Range: 2.6589. Min Range: -2.6589

Max Act: 2.3979. Min Act: -0.0000

Data Index: 1369353 (Python Code)

Max Activating Token Index: 1009

Text #4

Max Range: 2.6589. Min Range: -2.6589

Max Act: 2.4777. Min Act: -0.0001

Data Index: 1528295 (Python Code)

Max Activating Token Index: 272

Text #5

Max Range: 2.6589. Min Range: -2.6589

Max Act: 2.2830. Min Act: -0.0000

Data Index: 1364469 (Python Code)

Max Activating Token Index: 923

Text #6

Max Range: 2.6589. Min Range: -2.6589

Max Act: 2.1433. Min Act: -0.0000

Data Index: 1606850 (Python Code)

Max Activating Token Index: 452

Text #7

Max Range: 2.6589. Min Range: -2.6589

Max Act: 2.2335. Min Act: -0.0000

Data Index: 1365352 (Python Code)

Max Activating Token Index: 32

Text #8

Max Range: 2.6589. Min Range: -2.6589

Max Act: 2.1018. Min Act: -0.0000

Data Index: 1618172 (Python Code)

Max Activating Token Index: 255

Text #9

Max Range: 2.6589. Min Range: -2.6589

Max Act: 2.3318. Min Act: -0.0001

Data Index: 1484155 (Python Code)

Max Activating Token Index: 220

Text #10

Max Range: 2.6589. Min Range: -2.6589

Max Act: 2.3081. Min Act: -0.0000

Data Index: 1655747 (Python Code)

Max Activating Token Index: 56

Text #11

Max Range: 2.6589. Min Range: -2.6589

Max Act: 2.0747. Min Act: -0.0000

Data Index: 1646029 (Python Code)

Max Activating Token Index: 953

Text #12

Max Range: 2.6589. Min Range: -2.6589

Max Act: 2.1116. Min Act: -0.0001

Data Index: 1471543 (Python Code)

Max Activating Token Index: 622

Text #13

Max Range: 2.6589. Min Range: -2.6589

Max Act: 2.1810. Min Act: -0.0000

Data Index: 1514286 (Python Code)

Max Activating Token Index: 147

Text #14

Max Range: 2.6589. Min Range: -2.6589

Max Act: 2.2670. Min Act: -0.0000

Data Index: 1505978 (Python Code)

Max Activating Token Index: 552

Text #15

Max Range: 2.6589. Min Range: -2.6589

Max Act: 2.1132. Min Act: -0.0000

Data Index: 1633848 (Python Code)

Max Activating Token Index: 211

Text #16

Max Range: 2.6589. Min Range: -2.6589

Max Act: 2.1024. Min Act: -0.0001

Data Index: 1484274 (Python Code)

Max Activating Token Index: 904

Text #17

Max Range: 2.6589. Min Range: -2.6589

Max Act: 2.0727. Min Act: -0.0000

Data Index: 1639819 (Python Code)

Max Activating Token Index: 147

Text #18

Max Range: 2.6589. Min Range: -2.6589

Max Act: 2.0207. Min Act: -0.0001

Data Index: 1573170 (Python Code)

Max Activating Token Index: 921

Text #19

Max Range: 2.6589. Min Range: -2.6589

Max Act: 2.0398. Min Act: -0.0000

Data Index: 1424281 (Python Code)

Max Activating Token Index: 882