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

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

Neuron 3760 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.3481. Min Act: -0.0000

Data Index: 1469687 (Python Code)

Max Activating Token Index: 541

Text #1

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.2577. Min Act: -0.0000

Data Index: 1476032 (Python Code)

Max Activating Token Index: 453

Text #2

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.3981. Min Act: -0.0000

Data Index: 1457639 (Python Code)

Max Activating Token Index: 1005

Text #3

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.1838. Min Act: -0.0000

Data Index: 1603181 (Python Code)

Max Activating Token Index: 316

Text #4

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.2142. Min Act: -0.0000

Data Index: 1655823 (Python Code)

Max Activating Token Index: 125

Text #5

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.9956. Min Act: -0.0000

Data Index: 1574216 (Python Code)

Max Activating Token Index: 24

Text #6

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.1170. Min Act: -0.0000

Data Index: 1493490 (Python Code)

Max Activating Token Index: 129

Text #7

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.0350. Min Act: -0.0001

Data Index: 1431170 (Python Code)

Max Activating Token Index: 709

Text #8

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1413589 (Python Code)

Max Activating Token Index: 836

Text #9

Max Range: 1.3981. Min Range: -1.3981

Max Act: 1.0649. Min Act: -0.0001

Data Index: 1534114 (Python Code)

Max Activating Token Index: 941

Text #10

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.9657. Min Act: -0.0000

Data Index: 1397481 (Python Code)

Max Activating Token Index: 789

Text #11

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.9862. Min Act: -0.0000

Data Index: 1423845 (Python Code)

Max Activating Token Index: 219

Text #12

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.9088. Min Act: -0.0000

Data Index: 1586808 (Python Code)

Max Activating Token Index: 139

Text #13

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.8868. Min Act: -0.0000

Data Index: 1559320 (Python Code)

Max Activating Token Index: 107

Text #14

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.9681. Min Act: -0.0000

Data Index: 1369972 (Python Code)

Max Activating Token Index: 520

Text #15

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.9501. Min Act: -0.0000

Data Index: 1388547 (Python Code)

Max Activating Token Index: 431

Text #16

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.9715. Min Act: -0.0000

Data Index: 1561387 (Python Code)

Max Activating Token Index: 560

Text #17

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.8424. Min Act: -0.0000

Data Index: 1364876 (Python Code)

Max Activating Token Index: 976

Text #18

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.9296. Min Act: -0.0000

Data Index: 1594132 (Python Code)

Max Activating Token Index: 219

Text #19

Max Range: 1.3981. Min Range: -1.3981

Max Act: 0.8813. Min Act: -0.0000

Data Index: 1570746 (Python Code)

Max Activating Token Index: 885