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

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

Neuron 1311 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9669. Min Range: -1.9669

Max Act: 1.9669. Min Act: -0.0000

Data Index: 1453070 (Python Code)

Max Activating Token Index: 646

Text #1

Max Range: 1.9669. Min Range: -1.9669

Max Act: 1.6006. Min Act: -0.0000

Data Index: 1412374 (Python Code)

Max Activating Token Index: 275

Text #2

Max Range: 1.9669. Min Range: -1.9669

Max Act: 1.6468. Min Act: -0.0000

Data Index: 1573166 (Python Code)

Max Activating Token Index: 434

Text #3

Max Range: 1.9669. Min Range: -1.9669

Max Act: 1.4465. Min Act: -0.0000

Data Index: 1449486 (Python Code)

Max Activating Token Index: 659

Text #4

Max Range: 1.9669. Min Range: -1.9669

Max Act: 1.4548. Min Act: -0.0000

Data Index: 1436601 (Python Code)

Max Activating Token Index: 164

Text #5

Max Range: 1.9669. Min Range: -1.9669

Max Act: 1.5589. Min Act: -0.0000

Data Index: 1407838 (Python Code)

Max Activating Token Index: 414

Text #6

Max Range: 1.9669. Min Range: -1.9669

Max Act: 1.4151. Min Act: -0.0000

Data Index: 1539885 (Python Code)

Max Activating Token Index: 836

Text #7

Max Range: 1.9669. Min Range: -1.9669

Max Act: 1.2961. Min Act: -0.0000

Data Index: 1606174 (Python Code)

Max Activating Token Index: 539

Text #8

Max Range: 1.9669. Min Range: -1.9669

Max Act: 1.4214. Min Act: -0.0000

Data Index: 1584143 (Python Code)

Max Activating Token Index: 545

Text #9

Max Range: 1.9669. Min Range: -1.9669

Max Act: 1.3321. Min Act: -0.0000

Data Index: 1431227 (Python Code)

Max Activating Token Index: 377

Text #10

Max Range: 1.9669. Min Range: -1.9669

Max Act: 1.1025. Min Act: -0.0000

Data Index: 1527576 (Python Code)

Max Activating Token Index: 741

Text #11

Max Range: 1.9669. Min Range: -1.9669

Max Act: 1.3771. Min Act: -0.0000

Data Index: 1642965 (Python Code)

Max Activating Token Index: 963

Text #12

Max Range: 1.9669. Min Range: -1.9669

Max Act: 1.2711. Min Act: -0.0000

Data Index: 1385935 (Python Code)

Max Activating Token Index: 12

Text #13

Max Range: 1.9669. Min Range: -1.9669

Max Act: 1.3006. Min Act: -0.0000

Data Index: 1598944 (Python Code)

Max Activating Token Index: 1009

Text #14

Max Range: 1.9669. Min Range: -1.9669

Max Act: 1.3262. Min Act: -0.0000

Data Index: 1646577 (Python Code)

Max Activating Token Index: 521

Text #15

Max Range: 1.9669. Min Range: -1.9669

Max Act: 1.3530. Min Act: -0.0001

Data Index: 1483979 (Python Code)

Max Activating Token Index: 148

Text #16

Max Range: 1.9669. Min Range: -1.9669

Max Act: 1.3265. Min Act: -0.0000

Data Index: 1476443 (Python Code)

Max Activating Token Index: 419

Text #17

Max Range: 1.9669. Min Range: -1.9669

Max Act: 1.2999. Min Act: -0.0000

Data Index: 1486305 (Python Code)

Max Activating Token Index: 278

Text #18

Max Range: 1.9669. Min Range: -1.9669

Max Act: 1.1757. Min Act: -0.0000

Data Index: 1386656 (Python Code)

Max Activating Token Index: 581

Text #19

Max Range: 1.9669. Min Range: -1.9669

Max Act: 1.1601. Min Act: -0.0000

Data Index: 1637063 (Python Code)

Max Activating Token Index: 99