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

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

Neuron 500 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.6767. Min Act: -0.0001

Data Index: 1564895 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.6290. Min Act: -0.0001

Data Index: 1648693 (Python Code)

Max Activating Token Index: 22

Text #2

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.5508. Min Act: -0.0001

Data Index: 1464389 (Python Code)

Max Activating Token Index: 20

Text #3

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.5588. Min Act: -0.0001

Data Index: 1406327 (Python Code)

Max Activating Token Index: 63

Text #4

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.5300. Min Act: -0.0001

Data Index: 1399365 (Python Code)

Max Activating Token Index: 24

Text #5

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.5110. Min Act: -0.0001

Data Index: 1483185 (Python Code)

Max Activating Token Index: 103

Text #6

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4936. Min Act: -0.0001

Data Index: 1545920 (Python Code)

Max Activating Token Index: 34

Text #7

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4321. Min Act: -0.0001

Data Index: 1374965 (Python Code)

Max Activating Token Index: 940

Text #8

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4275. Min Act: -0.0001

Data Index: 1409779 (Python Code)

Max Activating Token Index: 19

Text #9

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4174. Min Act: -0.0001

Data Index: 1495568 (Python Code)

Max Activating Token Index: 942

Text #10

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4454. Min Act: -0.0001

Data Index: 1412203 (Python Code)

Max Activating Token Index: 19

Text #11

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4259. Min Act: -0.0001

Data Index: 1365227 (Python Code)

Max Activating Token Index: 22

Text #12

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4102. Min Act: -0.0001

Data Index: 1465675 (Python Code)

Max Activating Token Index: 18

Text #13

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.3922. Min Act: -0.0001

Data Index: 1542211 (Python Code)

Max Activating Token Index: 72

Text #14

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4178. Min Act: -0.0001

Data Index: 1397824 (Python Code)

Max Activating Token Index: 26

Text #15

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.4030. Min Act: -0.0001

Data Index: 1434438 (Python Code)

Max Activating Token Index: 22

Text #16

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.3963. Min Act: -0.0001

Data Index: 1618979 (Python Code)

Max Activating Token Index: 460

Text #17

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.3693. Min Act: -0.0001

Data Index: 1544263 (Python Code)

Max Activating Token Index: 105

Text #18

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.3807. Min Act: -0.0001

Data Index: 1501820 (Python Code)

Max Activating Token Index: 122

Text #19

Max Range: 0.6767. Min Range: -0.6767

Max Act: 0.3810. Min Act: -0.0001

Data Index: 1498427 (Python Code)

Max Activating Token Index: 22