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

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

Neuron 5027 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1041. Min Range: -1.1041

Max Act: 1.1041. Min Act: -0.0000

Data Index: 1639694 (Python Code)

Max Activating Token Index: 706

Text #1

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.9170. Min Act: -0.0000

Data Index: 1425361 (Python Code)

Max Activating Token Index: 88

Text #2

Max Range: 1.1041. Min Range: -1.1041

Max Act: 1.0020. Min Act: -0.0000

Data Index: 1454315 (Python Code)

Max Activating Token Index: 613

Text #3

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.9197. Min Act: -0.0000

Data Index: 1480039 (Python Code)

Max Activating Token Index: 547

Text #4

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.9292. Min Act: -0.0000

Data Index: 1425163 (Python Code)

Max Activating Token Index: 180

Text #5

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.9000. Min Act: -0.0000

Data Index: 1493264 (Python Code)

Max Activating Token Index: 1011

Text #6

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.9801. Min Act: -0.0000

Data Index: 1485968 (Python Code)

Max Activating Token Index: 196

Text #7

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.8624. Min Act: -0.0000

Data Index: 1505218 (Python Code)

Max Activating Token Index: 984

Text #8

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.8861. Min Act: -0.0000

Data Index: 1581563 (Python Code)

Max Activating Token Index: 872

Text #9

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.8242. Min Act: -0.0000

Data Index: 1634425 (Python Code)

Max Activating Token Index: 213

Text #10

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.8030. Min Act: -0.0000

Data Index: 1424745 (Python Code)

Max Activating Token Index: 697

Text #11

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.8865. Min Act: -0.0000

Data Index: 1382332 (Python Code)

Max Activating Token Index: 42

Text #12

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.8262. Min Act: -0.0000

Data Index: 1650332 (Python Code)

Max Activating Token Index: 258

Text #13

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1431597 (Python Code)

Max Activating Token Index: 549

Text #14

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.8415. Min Act: -0.0000

Data Index: 1645318 (Python Code)

Max Activating Token Index: 113

Text #15

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.7614. Min Act: -0.0000

Data Index: 1435813 (Python Code)

Max Activating Token Index: 312

Text #16

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.8032. Min Act: -0.0000

Data Index: 1372256 (Python Code)

Max Activating Token Index: 462

Text #17

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.8294. Min Act: -0.0000

Data Index: 1430629 (Python Code)

Max Activating Token Index: 747

Text #18

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.8366. Min Act: -0.0000

Data Index: 1599282 (Python Code)

Max Activating Token Index: 13

Text #19

Max Range: 1.1041. Min Range: -1.1041

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1479579 (Python Code)

Max Activating Token Index: 881