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

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

Neuron 3836 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: 2.6468. Min Range: -2.6468

Max Act: 2.6468. Min Act: -0.0000

Data Index: 1628417 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 2.6468. Min Range: -2.6468

Max Act: 2.2758. Min Act: -0.0000

Data Index: 1500584 (Python Code)

Max Activating Token Index: 159

Text #2

Max Range: 2.6468. Min Range: -2.6468

Max Act: 2.2636. Min Act: -0.0000

Data Index: 1556003 (Python Code)

Max Activating Token Index: 170

Text #3

Max Range: 2.6468. Min Range: -2.6468

Max Act: 2.2508. Min Act: -0.0000

Data Index: 1490571 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 2.6468. Min Range: -2.6468

Max Act: 2.2503. Min Act: -0.0000

Data Index: 1428827 (Python Code)

Max Activating Token Index: 4

Text #5

Max Range: 2.6468. Min Range: -2.6468

Max Act: 2.1092. Min Act: -0.0000

Data Index: 1623367 (Python Code)

Max Activating Token Index: 11

Text #6

Max Range: 2.6468. Min Range: -2.6468

Max Act: 2.2164. Min Act: -0.0000

Data Index: 1540366 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 2.6468. Min Range: -2.6468

Max Act: 2.3268. Min Act: -0.0000

Data Index: 1416514 (Python Code)

Max Activating Token Index: 726

Text #8

Max Range: 2.6468. Min Range: -2.6468

Max Act: 2.0681. Min Act: -0.0000

Data Index: 1384237 (Python Code)

Max Activating Token Index: 405

Text #9

Max Range: 2.6468. Min Range: -2.6468

Max Act: 2.2320. Min Act: -0.0000

Data Index: 1617519 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 2.6468. Min Range: -2.6468

Max Act: 2.1273. Min Act: -0.0000

Data Index: 1421883 (Python Code)

Max Activating Token Index: 7

Text #11

Max Range: 2.6468. Min Range: -2.6468

Max Act: 2.0856. Min Act: -0.0000

Data Index: 1574055 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 2.6468. Min Range: -2.6468

Max Act: 2.0831. Min Act: -0.0000

Data Index: 1364510 (Python Code)

Max Activating Token Index: 12

Text #13

Max Range: 2.6468. Min Range: -2.6468

Max Act: 2.0619. Min Act: -0.0000

Data Index: 1424553 (Python Code)

Max Activating Token Index: 13

Text #14

Max Range: 2.6468. Min Range: -2.6468

Max Act: 1.9999. Min Act: -0.0000

Data Index: 1524757 (Python Code)

Max Activating Token Index: 13

Text #15

Max Range: 2.6468. Min Range: -2.6468

Max Act: 2.0467. Min Act: -0.0000

Data Index: 1472237 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 2.6468. Min Range: -2.6468

Max Act: 2.0287. Min Act: -0.0000

Data Index: 1512826 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 2.6468. Min Range: -2.6468

Max Act: 2.1366. Min Act: -0.0000

Data Index: 1491433 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 2.6468. Min Range: -2.6468

Max Act: 2.0205. Min Act: -0.0000

Data Index: 1574419 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 2.6468. Min Range: -2.6468

Max Act: 2.0552. Min Act: -0.0000

Data Index: 1559609 (Python Code)

Max Activating Token Index: 8