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

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

Neuron 750 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6730. Min Range: -2.6730

Max Act: 2.6730. Min Act: -0.0000

Data Index: 1483217 (Python Code)

Max Activating Token Index: 59

Text #1

Max Range: 2.6730. Min Range: -2.6730

Max Act: 2.6119. Min Act: -0.0000

Data Index: 1505974 (Python Code)

Max Activating Token Index: 268

Text #2

Max Range: 2.6730. Min Range: -2.6730

Max Act: 2.3149. Min Act: -0.0000

Data Index: 1525454 (Python Code)

Max Activating Token Index: 859

Text #3

Max Range: 2.6730. Min Range: -2.6730

Max Act: 2.1101. Min Act: -0.0000

Data Index: 1434154 (Python Code)

Max Activating Token Index: 434

Text #4

Max Range: 2.6730. Min Range: -2.6730

Max Act: 1.9525. Min Act: -0.0000

Data Index: 1397071 (Python Code)

Max Activating Token Index: 327

Text #5

Max Range: 2.6730. Min Range: -2.6730

Max Act: 1.6417. Min Act: -0.0000

Data Index: 1542490 (Python Code)

Max Activating Token Index: 908

Text #6

Max Range: 2.6730. Min Range: -2.6730

Max Act: 1.5273. Min Act: -0.0000

Data Index: 1593920 (Python Code)

Max Activating Token Index: 491

Text #7

Max Range: 2.6730. Min Range: -2.6730

Max Act: 1.5260. Min Act: -0.0000

Data Index: 1368244 (Python Code)

Max Activating Token Index: 34

Text #8

Max Range: 2.6730. Min Range: -2.6730

Max Act: 1.4308. Min Act: -0.0000

Data Index: 1507491 (Python Code)

Max Activating Token Index: 549

Text #9

Max Range: 2.6730. Min Range: -2.6730

Max Act: 1.3211. Min Act: -0.0000

Data Index: 1649891 (Python Code)

Max Activating Token Index: 701

Text #10

Max Range: 2.6730. Min Range: -2.6730

Max Act: 1.1848. Min Act: -0.0000

Data Index: 1556938 (Python Code)

Max Activating Token Index: 832

Text #11

Max Range: 2.6730. Min Range: -2.6730

Max Act: 1.0979. Min Act: -0.0000

Data Index: 1430438 (Python Code)

Max Activating Token Index: 260

Text #12

Max Range: 2.6730. Min Range: -2.6730

Max Act: 1.1284. Min Act: -0.0000

Data Index: 1546722 (Python Code)

Max Activating Token Index: 683

Text #13

Max Range: 2.6730. Min Range: -2.6730

Max Act: 0.9730. Min Act: -0.0000

Data Index: 1492442 (Python Code)

Max Activating Token Index: 253

Text #14

Max Range: 2.6730. Min Range: -2.6730

Max Act: 0.9794. Min Act: -0.0000

Data Index: 1458883 (Python Code)

Max Activating Token Index: 290

Text #15

Max Range: 2.6730. Min Range: -2.6730

Max Act: 0.8546. Min Act: -0.0000

Data Index: 1422599 (Python Code)

Max Activating Token Index: 162

Text #16

Max Range: 2.6730. Min Range: -2.6730

Max Act: 0.8260. Min Act: -0.0000

Data Index: 1646549 (Python Code)

Max Activating Token Index: 585

Text #17

Max Range: 2.6730. Min Range: -2.6730

Max Act: 0.8246. Min Act: -0.0000

Data Index: 1588508 (Python Code)

Max Activating Token Index: 146

Text #18

Max Range: 2.6730. Min Range: -2.6730

Max Act: 0.8192. Min Act: -0.0000

Data Index: 1618380 (Python Code)

Max Activating Token Index: 546

Text #19

Max Range: 2.6730. Min Range: -2.6730

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1460740 (Python Code)

Max Activating Token Index: 310