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

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

Neuron 2004 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7988. Min Range: -1.7988

Max Act: 1.7988. Min Act: -0.0000

Data Index: 1635062 (Python Code)

Max Activating Token Index: 96

Text #1

Max Range: 1.7988. Min Range: -1.7988

Max Act: 1.6481. Min Act: -0.0000

Data Index: 1428191 (Python Code)

Max Activating Token Index: 299

Text #2

Max Range: 1.7988. Min Range: -1.7988

Max Act: 1.7459. Min Act: -0.0000

Data Index: 1650877 (Python Code)

Max Activating Token Index: 53

Text #3

Max Range: 1.7988. Min Range: -1.7988

Max Act: 1.6801. Min Act: -0.0000

Data Index: 1460572 (Python Code)

Max Activating Token Index: 125

Text #4

Max Range: 1.7988. Min Range: -1.7988

Max Act: 1.6109. Min Act: -0.0000

Data Index: 1571611 (Python Code)

Max Activating Token Index: 156

Text #5

Max Range: 1.7988. Min Range: -1.7988

Max Act: 1.6405. Min Act: -0.0000

Data Index: 1652593 (Python Code)

Max Activating Token Index: 129

Text #6

Max Range: 1.7988. Min Range: -1.7988

Max Act: 1.3331. Min Act: -0.0000

Data Index: 1533740 (Python Code)

Max Activating Token Index: 144

Text #7

Max Range: 1.7988. Min Range: -1.7988

Max Act: 1.4860. Min Act: -0.0000

Data Index: 1636004 (Python Code)

Max Activating Token Index: 223

Text #8

Max Range: 1.7988. Min Range: -1.7988

Max Act: 1.4016. Min Act: -0.0000

Data Index: 1381245 (Python Code)

Max Activating Token Index: 673

Text #9

Max Range: 1.7988. Min Range: -1.7988

Max Act: 1.3907. Min Act: -0.0000

Data Index: 1428321 (Python Code)

Max Activating Token Index: 41

Text #10

Max Range: 1.7988. Min Range: -1.7988

Max Act: 1.3601. Min Act: -0.0000

Data Index: 1617668 (Python Code)

Max Activating Token Index: 400

Text #11

Max Range: 1.7988. Min Range: -1.7988

Max Act: 1.2618. Min Act: -0.0000

Data Index: 1385915 (Python Code)

Max Activating Token Index: 772

Text #12

Max Range: 1.7988. Min Range: -1.7988

Max Act: 1.2460. Min Act: -0.0000

Data Index: 1439592 (Python Code)

Max Activating Token Index: 851

Text #13

Max Range: 1.7988. Min Range: -1.7988

Max Act: 1.2692. Min Act: -0.0000

Data Index: 1481572 (Python Code)

Max Activating Token Index: 332

Text #14

Max Range: 1.7988. Min Range: -1.7988

Max Act: 1.3423. Min Act: -0.0000

Data Index: 1374884 (Python Code)

Max Activating Token Index: 241

Text #15

Max Range: 1.7988. Min Range: -1.7988

Max Act: 1.2560. Min Act: -0.0000

Data Index: 1503860 (Python Code)

Max Activating Token Index: 368

Text #16

Max Range: 1.7988. Min Range: -1.7988

Max Act: 1.3343. Min Act: -0.0000

Data Index: 1405231 (Python Code)

Max Activating Token Index: 362

Text #17

Max Range: 1.7988. Min Range: -1.7988

Max Act: 1.2126. Min Act: -0.0000

Data Index: 1411573 (Python Code)

Max Activating Token Index: 60

Text #18

Max Range: 1.7988. Min Range: -1.7988

Max Act: 1.1994. Min Act: -0.0000

Data Index: 1415564 (Python Code)

Max Activating Token Index: 58

Text #19

Max Range: 1.7988. Min Range: -1.7988

Max Act: 1.1170. Min Act: -0.0000

Data Index: 1444857 (Python Code)

Max Activating Token Index: 766