Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4030 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1098. Min Range: -1.1098

Max Act: 1.1098. Min Act: -0.0001

Data Index: 1527202 (Python Code)

Max Activating Token Index: 389

Text #1

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.9897. Min Act: -0.0001

Data Index: 1589985 (Python Code)

Max Activating Token Index: 283

Text #2

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.9668. Min Act: -0.0001

Data Index: 1440856 (Python Code)

Max Activating Token Index: 47

Text #3

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.9352. Min Act: -0.0001

Data Index: 1394491 (Python Code)

Max Activating Token Index: 839

Text #4

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.9773. Min Act: -0.0001

Data Index: 1494891 (Python Code)

Max Activating Token Index: 480

Text #5

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.9129. Min Act: -0.0001

Data Index: 1600423 (Python Code)

Max Activating Token Index: 638

Text #6

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.8809. Min Act: -0.0001

Data Index: 1606954 (Python Code)

Max Activating Token Index: 327

Text #7

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.8024. Min Act: -0.0001

Data Index: 1583828 (Python Code)

Max Activating Token Index: 223

Text #8

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.8866. Min Act: -0.0001

Data Index: 1426044 (Python Code)

Max Activating Token Index: 41

Text #9

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.8563. Min Act: -0.0001

Data Index: 1453763 (Python Code)

Max Activating Token Index: 443

Text #10

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.8747. Min Act: -0.0001

Data Index: 1368821 (Python Code)

Max Activating Token Index: 250

Text #11

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.7676. Min Act: -0.0001

Data Index: 1636493 (Python Code)

Max Activating Token Index: 995

Text #12

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.7522. Min Act: -0.0001

Data Index: 1393958 (Python Code)

Max Activating Token Index: 274

Text #13

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.8004. Min Act: -0.0001

Data Index: 1566029 (Python Code)

Max Activating Token Index: 269

Text #14

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.7551. Min Act: -0.0001

Data Index: 1380657 (Python Code)

Max Activating Token Index: 55

Text #15

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.8410. Min Act: -0.0001

Data Index: 1622756 (Python Code)

Max Activating Token Index: 41

Text #16

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.7411. Min Act: -0.0001

Data Index: 1532390 (Python Code)

Max Activating Token Index: 552

Text #17

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.7880. Min Act: -0.0001

Data Index: 1425191 (Python Code)

Max Activating Token Index: 607

Text #18

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.8314. Min Act: -0.0001

Data Index: 1540600 (Python Code)

Max Activating Token Index: 588

Text #19

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.8001. Min Act: -0.0001

Data Index: 1414344 (Python Code)

Max Activating Token Index: 370