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

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

Neuron 3311 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.7903. Min Act: -0.0001

Data Index: 1632051 (Python Code)

Max Activating Token Index: 612

Text #1

Max Range: 1.1753. Min Range: -1.1753

Max Act: 1.1406. Min Act: -0.0001

Data Index: 1598400 (Python Code)

Max Activating Token Index: 272

Text #2

Max Range: 1.1753. Min Range: -1.1753

Max Act: 1.1200. Min Act: -0.0001

Data Index: 1575151 (Python Code)

Max Activating Token Index: 602

Text #3

Max Range: 1.1753. Min Range: -1.1753

Max Act: 1.0604. Min Act: -0.0001

Data Index: 1609802 (Python Code)

Max Activating Token Index: 137

Text #4

Max Range: 1.1753. Min Range: -1.1753

Max Act: 1.1046. Min Act: -0.0001

Data Index: 1440100 (Python Code)

Max Activating Token Index: 81

Text #5

Max Range: 1.1753. Min Range: -1.1753

Max Act: 1.0276. Min Act: -0.0001

Data Index: 1417204 (Python Code)

Max Activating Token Index: 668

Text #6

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9851. Min Act: -0.0001

Data Index: 1557941 (Python Code)

Max Activating Token Index: 718

Text #7

Max Range: 1.1753. Min Range: -1.1753

Max Act: 1.1753. Min Act: -0.0001

Data Index: 1493894 (Python Code)

Max Activating Token Index: 690

Text #8

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9762. Min Act: -0.0001

Data Index: 1498128 (Python Code)

Max Activating Token Index: 528

Text #9

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.8354. Min Act: -0.0001

Data Index: 1361265 (Python Code)

Max Activating Token Index: 809

Text #10

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9251. Min Act: -0.0001

Data Index: 1395758 (Python Code)

Max Activating Token Index: 51

Text #11

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9673. Min Act: -0.0001

Data Index: 1490294 (Python Code)

Max Activating Token Index: 363

Text #12

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9346. Min Act: -0.0001

Data Index: 1506106 (Python Code)

Max Activating Token Index: 711

Text #13

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9231. Min Act: -0.0001

Data Index: 1377370 (Python Code)

Max Activating Token Index: 524

Text #14

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9457. Min Act: -0.0001

Data Index: 1581666 (Python Code)

Max Activating Token Index: 52

Text #15

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9026. Min Act: -0.0001

Data Index: 1364761 (Python Code)

Max Activating Token Index: 96

Text #16

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.7824. Min Act: -0.0001

Data Index: 1386448 (Python Code)

Max Activating Token Index: 686

Text #17

Max Range: 1.1753. Min Range: -1.1753

Max Act: 1.0005. Min Act: -0.0001

Data Index: 1611086 (Python Code)

Max Activating Token Index: 428

Text #18

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.8815. Min Act: -0.0001

Data Index: 1378908 (Python Code)

Max Activating Token Index: 499

Text #19

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.8896. Min Act: -0.0001

Data Index: 1431861 (Python Code)

Max Activating Token Index: 69