Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 306 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3616. Min Range: -2.3616

Max Act: 2.2856. Min Act: -0.0000

Data Index: 1469914 (Python Code)

Max Activating Token Index: 160

Text #1

Max Range: 2.3616. Min Range: -2.3616

Max Act: 2.3616. Min Act: -0.0000

Data Index: 1600894 (Python Code)

Max Activating Token Index: 104

Text #2

Max Range: 2.3616. Min Range: -2.3616

Max Act: 2.3005. Min Act: -0.0000

Data Index: 1555718 (Python Code)

Max Activating Token Index: 122

Text #3

Max Range: 2.3616. Min Range: -2.3616

Max Act: 2.0122. Min Act: -0.0000

Data Index: 1508951 (Python Code)

Max Activating Token Index: 247

Text #4

Max Range: 2.3616. Min Range: -2.3616

Max Act: 2.0951. Min Act: -0.0000

Data Index: 1432019 (Python Code)

Max Activating Token Index: 257

Text #5

Max Range: 2.3616. Min Range: -2.3616

Max Act: 2.1812. Min Act: -0.0000

Data Index: 1389000 (Python Code)

Max Activating Token Index: 141

Text #6

Max Range: 2.3616. Min Range: -2.3616

Max Act: 1.8344. Min Act: -0.0000

Data Index: 1452902 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 2.3616. Min Range: -2.3616

Max Act: 1.7437. Min Act: -0.0000

Data Index: 1443024 (Python Code)

Max Activating Token Index: 35

Text #8

Max Range: 2.3616. Min Range: -2.3616

Max Act: 1.7114. Min Act: -0.0000

Data Index: 1474393 (Python Code)

Max Activating Token Index: 27

Text #9

Max Range: 2.3616. Min Range: -2.3616

Max Act: 1.6895. Min Act: -0.0000

Data Index: 1466784 (Python Code)

Max Activating Token Index: 37

Text #10

Max Range: 2.3616. Min Range: -2.3616

Max Act: 1.6648. Min Act: -0.0000

Data Index: 1465512 (Python Code)

Max Activating Token Index: 90

Text #11

Max Range: 2.3616. Min Range: -2.3616

Max Act: 1.7577. Min Act: -0.0000

Data Index: 1503545 (Python Code)

Max Activating Token Index: 25

Text #12

Max Range: 2.3616. Min Range: -2.3616

Max Act: 1.7308. Min Act: -0.0000

Data Index: 1650497 (Python Code)

Max Activating Token Index: 562

Text #13

Max Range: 2.3616. Min Range: -2.3616

Max Act: 1.6268. Min Act: -0.0000

Data Index: 1487010 (Python Code)

Max Activating Token Index: 751

Text #14

Max Range: 2.3616. Min Range: -2.3616

Max Act: 1.6290. Min Act: -0.0000

Data Index: 1428244 (Python Code)

Max Activating Token Index: 162

Text #15

Max Range: 2.3616. Min Range: -2.3616

Max Act: 1.5279. Min Act: -0.0000

Data Index: 1615344 (Python Code)

Max Activating Token Index: 69

Text #16

Max Range: 2.3616. Min Range: -2.3616

Max Act: 1.5233. Min Act: -0.0000

Data Index: 1407015 (Python Code)

Max Activating Token Index: 478

Text #17

Max Range: 2.3616. Min Range: -2.3616

Max Act: 1.5139. Min Act: -0.0000

Data Index: 1558829 (Python Code)

Max Activating Token Index: 38

Text #18

Max Range: 2.3616. Min Range: -2.3616

Max Act: 1.4890. Min Act: -0.0000

Data Index: 1381731 (Python Code)

Max Activating Token Index: 615

Text #19

Max Range: 2.3616. Min Range: -2.3616

Max Act: 1.4923. Min Act: -0.0000

Data Index: 1379882 (Python Code)

Max Activating Token Index: 860