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

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

Neuron 552 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: 2.2488. Min Range: -2.2488

Max Act: 2.1838. Min Act: -0.0000

Data Index: 1584686 (Python Code)

Max Activating Token Index: 55

Text #1

Max Range: 2.2488. Min Range: -2.2488

Max Act: 2.2488. Min Act: -0.0000

Data Index: 1575149 (Python Code)

Max Activating Token Index: 707

Text #2

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.9590. Min Act: -0.0000

Data Index: 1514191 (Python Code)

Max Activating Token Index: 64

Text #3

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.9480. Min Act: -0.0000

Data Index: 1649915 (Python Code)

Max Activating Token Index: 201

Text #4

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.9461. Min Act: -0.0000

Data Index: 1495062 (Python Code)

Max Activating Token Index: 595

Text #5

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.8844. Min Act: -0.0000

Data Index: 1511719 (Python Code)

Max Activating Token Index: 699

Text #6

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.6888. Min Act: -0.0000

Data Index: 1559787 (Python Code)

Max Activating Token Index: 194

Text #7

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.6700. Min Act: -0.0000

Data Index: 1477197 (Python Code)

Max Activating Token Index: 227

Text #8

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.6708. Min Act: -0.0000

Data Index: 1479420 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.6688. Min Act: -0.0000

Data Index: 1440653 (Python Code)

Max Activating Token Index: 175

Text #10

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.6046. Min Act: -0.0000

Data Index: 1580162 (Python Code)

Max Activating Token Index: 98

Text #11

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.5977. Min Act: -0.0000

Data Index: 1461013 (Python Code)

Max Activating Token Index: 568

Text #12

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.6761. Min Act: -0.0000

Data Index: 1517705 (Python Code)

Max Activating Token Index: 504

Text #13

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.6578. Min Act: -0.0000

Data Index: 1609364 (Python Code)

Max Activating Token Index: 614

Text #14

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.7090. Min Act: -0.0000

Data Index: 1541905 (Python Code)

Max Activating Token Index: 315

Text #15

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.5883. Min Act: -0.0000

Data Index: 1634197 (Python Code)

Max Activating Token Index: 40

Text #16

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.5597. Min Act: -0.0000

Data Index: 1625609 (Python Code)

Max Activating Token Index: 179

Text #17

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.3235. Min Act: -0.0000

Data Index: 1417929 (Python Code)

Max Activating Token Index: 437

Text #18

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.5801. Min Act: -0.0000

Data Index: 1449824 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.4742. Min Act: -0.0000

Data Index: 1432513 (Python Code)

Max Activating Token Index: 225