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

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

Neuron 1032 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0975. Min Range: -2.0975

Max Act: 2.0975. Min Act: -0.0000

Data Index: 1445015 (Python Code)

Max Activating Token Index: 306

Text #1

Max Range: 2.0975. Min Range: -2.0975

Max Act: 2.0156. Min Act: -0.0000

Data Index: 1569061 (Python Code)

Max Activating Token Index: 614

Text #2

Max Range: 2.0975. Min Range: -2.0975

Max Act: 1.7934. Min Act: -0.0000

Data Index: 1408890 (Python Code)

Max Activating Token Index: 323

Text #3

Max Range: 2.0975. Min Range: -2.0975

Max Act: 1.8095. Min Act: -0.0000

Data Index: 1484297 (Python Code)

Max Activating Token Index: 637

Text #4

Max Range: 2.0975. Min Range: -2.0975

Max Act: 1.7036. Min Act: -0.0000

Data Index: 1565020 (Python Code)

Max Activating Token Index: 43

Text #5

Max Range: 2.0975. Min Range: -2.0975

Max Act: 1.6876. Min Act: -0.0000

Data Index: 1416064 (Python Code)

Max Activating Token Index: 571

Text #6

Max Range: 2.0975. Min Range: -2.0975

Max Act: 1.6574. Min Act: -0.0001

Data Index: 1651098 (Python Code)

Max Activating Token Index: 574

Text #7

Max Range: 2.0975. Min Range: -2.0975

Max Act: 1.7061. Min Act: -0.0000

Data Index: 1413917 (Python Code)

Max Activating Token Index: 79

Text #8

Max Range: 2.0975. Min Range: -2.0975

Max Act: 1.8151. Min Act: -0.0000

Data Index: 1406340 (Python Code)

Max Activating Token Index: 863

Text #9

Max Range: 2.0975. Min Range: -2.0975

Max Act: 1.5562. Min Act: -0.0000

Data Index: 1431740 (Python Code)

Max Activating Token Index: 161

Text #10

Max Range: 2.0975. Min Range: -2.0975

Max Act: 1.6117. Min Act: -0.0000

Data Index: 1636744 (Python Code)

Max Activating Token Index: 282

Text #11

Max Range: 2.0975. Min Range: -2.0975

Max Act: 1.5025. Min Act: -0.0000

Data Index: 1489392 (Python Code)

Max Activating Token Index: 554

Text #12

Max Range: 2.0975. Min Range: -2.0975

Max Act: 1.4872. Min Act: -0.0000

Data Index: 1474254 (Python Code)

Max Activating Token Index: 40

Text #13

Max Range: 2.0975. Min Range: -2.0975

Max Act: 1.4148. Min Act: -0.0000

Data Index: 1458386 (Python Code)

Max Activating Token Index: 555

Text #14

Max Range: 2.0975. Min Range: -2.0975

Max Act: 1.5511. Min Act: -0.0000

Data Index: 1654714 (Python Code)

Max Activating Token Index: 527

Text #15

Max Range: 2.0975. Min Range: -2.0975

Max Act: 1.4425. Min Act: -0.0000

Data Index: 1535336 (Python Code)

Max Activating Token Index: 515

Text #16

Max Range: 2.0975. Min Range: -2.0975

Max Act: 1.4817. Min Act: -0.0000

Data Index: 1648918 (Python Code)

Max Activating Token Index: 78

Text #17

Max Range: 2.0975. Min Range: -2.0975

Max Act: 1.5099. Min Act: -0.0000

Data Index: 1362756 (Python Code)

Max Activating Token Index: 345

Text #18

Max Range: 2.0975. Min Range: -2.0975

Max Act: 1.5537. Min Act: -0.0000

Data Index: 1497865 (Python Code)

Max Activating Token Index: 893

Text #19

Max Range: 2.0975. Min Range: -2.0975

Max Act: 1.5016. Min Act: -0.0000

Data Index: 1381420 (Python Code)

Max Activating Token Index: 513