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

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

Neuron 525 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1442. Min Range: -1.1442

Max Act: 1.1442. Min Act: -0.0000

Data Index: 1650348 (Python Code)

Max Activating Token Index: 510

Text #1

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.8672. Min Act: -0.0000

Data Index: 1439257 (Python Code)

Max Activating Token Index: 194

Text #2

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.8788. Min Act: -0.0000

Data Index: 1618584 (Python Code)

Max Activating Token Index: 360

Text #3

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.8174. Min Act: -0.0000

Data Index: 1496419 (Python Code)

Max Activating Token Index: 341

Text #4

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.7863. Min Act: -0.0000

Data Index: 1635380 (Python Code)

Max Activating Token Index: 927

Text #5

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.7645. Min Act: -0.0000

Data Index: 1433268 (Python Code)

Max Activating Token Index: 382

Text #6

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.6948. Min Act: -0.0000

Data Index: 1540028 (Python Code)

Max Activating Token Index: 462

Text #7

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.7723. Min Act: -0.0000

Data Index: 1397373 (Python Code)

Max Activating Token Index: 233

Text #8

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1598036 (Python Code)

Max Activating Token Index: 456

Text #9

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1370393 (Python Code)

Max Activating Token Index: 360

Text #10

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1441579 (Python Code)

Max Activating Token Index: 33

Text #11

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.6692. Min Act: -0.0000

Data Index: 1629035 (Python Code)

Max Activating Token Index: 32

Text #12

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.6784. Min Act: -0.0000

Data Index: 1633223 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1524948 (Python Code)

Max Activating Token Index: 674

Text #14

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.5734. Min Act: -0.0000

Data Index: 1412787 (Python Code)

Max Activating Token Index: 430

Text #15

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1509846 (Python Code)

Max Activating Token Index: 198

Text #16

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.5900. Min Act: -0.0000

Data Index: 1615368 (Python Code)

Max Activating Token Index: 469

Text #17

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.5682. Min Act: -0.0000

Data Index: 1451305 (Python Code)

Max Activating Token Index: 92

Text #18

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.5686. Min Act: -0.0000

Data Index: 1509717 (Python Code)

Max Activating Token Index: 625

Text #19

Max Range: 1.1442. Min Range: -1.1442

Max Act: 0.5773. Min Act: -0.0000

Data Index: 1504509 (Python Code)

Max Activating Token Index: 961