Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1026 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.5217. Min Act: -0.0003

Data Index: 1544756 (Python Code)

Max Activating Token Index: 63

Text #1

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.5373. Min Act: -0.0003

Data Index: 1406978 (Python Code)

Max Activating Token Index: 74

Text #2

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.5161. Min Act: -0.0003

Data Index: 1526077 (Python Code)

Max Activating Token Index: 127

Text #3

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.4794. Min Act: -0.0003

Data Index: 1370108 (Python Code)

Max Activating Token Index: 91

Text #4

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.4889. Min Act: -0.0003

Data Index: 1387165 (Python Code)

Max Activating Token Index: 204

Text #5

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.4866. Min Act: -0.0003

Data Index: 1417832 (Python Code)

Max Activating Token Index: 148

Text #6

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.4697. Min Act: -0.0003

Data Index: 1648050 (Python Code)

Max Activating Token Index: 83

Text #7

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.4804. Min Act: -0.0003

Data Index: 1569542 (Python Code)

Max Activating Token Index: 149

Text #8

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.4796. Min Act: -0.0003

Data Index: 1604374 (Python Code)

Max Activating Token Index: 138

Text #9

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.4767. Min Act: -0.0003

Data Index: 1614024 (Python Code)

Max Activating Token Index: 387

Text #10

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.5089. Min Act: -0.0003

Data Index: 1497610 (Python Code)

Max Activating Token Index: 172

Text #11

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.4611. Min Act: -0.0003

Data Index: 1375970 (Python Code)

Max Activating Token Index: 220

Text #12

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.4725. Min Act: -0.0003

Data Index: 1520589 (Python Code)

Max Activating Token Index: 217

Text #13

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.4733. Min Act: -0.0003

Data Index: 1492103 (Python Code)

Max Activating Token Index: 96

Text #14

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.4853. Min Act: -0.0003

Data Index: 1498535 (Python Code)

Max Activating Token Index: 65

Text #15

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.4583. Min Act: -0.0003

Data Index: 1627829 (Python Code)

Max Activating Token Index: 186

Text #16

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.4677. Min Act: -0.0003

Data Index: 1474974 (Python Code)

Max Activating Token Index: 41

Text #17

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.4384. Min Act: -0.0003

Data Index: 1529720 (Python Code)

Max Activating Token Index: 70

Text #18

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.4820. Min Act: -0.0003

Data Index: 1519977 (Python Code)

Max Activating Token Index: 124

Text #19

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.4520. Min Act: -0.0003

Data Index: 1484624 (Python Code)

Max Activating Token Index: 264