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

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

Neuron 1380 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.7188. Min Act: -0.0000

Data Index: 1496224 (Python Code)

Max Activating Token Index: 123

Text #1

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1389826 (Python Code)

Max Activating Token Index: 291

Text #2

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.7306. Min Act: -0.0000

Data Index: 1487625 (Python Code)

Max Activating Token Index: 347

Text #3

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.7595. Min Act: -0.0000

Data Index: 1424397 (Python Code)

Max Activating Token Index: 405

Text #4

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.7817. Min Act: -0.0000

Data Index: 1525215 (Python Code)

Max Activating Token Index: 171

Text #5

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.6636. Min Act: -0.0000

Data Index: 1488783 (Python Code)

Max Activating Token Index: 970

Text #6

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.6928. Min Act: -0.0000

Data Index: 1558084 (Python Code)

Max Activating Token Index: 220

Text #7

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.7542. Min Act: -0.0000

Data Index: 1561617 (Python Code)

Max Activating Token Index: 387

Text #8

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.6355. Min Act: -0.0000

Data Index: 1382734 (Python Code)

Max Activating Token Index: 68

Text #9

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1085141 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1374293 (Python Code)

Max Activating Token Index: 737

Text #11

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.6767. Min Act: -0.0000

Data Index: 1490060 (Python Code)

Max Activating Token Index: 257

Text #12

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1530940 (Python Code)

Max Activating Token Index: 779

Text #13

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1387527 (Python Code)

Max Activating Token Index: 69

Text #14

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1478384 (Python Code)

Max Activating Token Index: 399

Text #15

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.4694. Min Act: -0.0000

Data Index: 1454914 (Python Code)

Max Activating Token Index: 439

Text #16

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.5237. Min Act: -0.0000

Data Index: 1419871 (Python Code)

Max Activating Token Index: 902

Text #17

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.5251. Min Act: -0.0000

Data Index: 1383851 (Python Code)

Max Activating Token Index: 507

Text #18

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.5478. Min Act: -0.0000

Data Index: 1450353 (Python Code)

Max Activating Token Index: 32

Text #19

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.4867. Min Act: -0.0000

Data Index: 1544868 (Python Code)

Max Activating Token Index: 654