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

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

Neuron 590 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.8363. Min Act: -0.0001

Data Index: 1444779 (Python Code)

Max Activating Token Index: 98

Text #1

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.9098. Min Act: -0.0001

Data Index: 1590761 (Python Code)

Max Activating Token Index: 185

Text #2

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.8472. Min Act: -0.0001

Data Index: 1511205 (Python Code)

Max Activating Token Index: 39

Text #3

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.8314. Min Act: -0.0001

Data Index: 1410904 (Python Code)

Max Activating Token Index: 204

Text #4

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7900. Min Act: -0.0002

Data Index: 1604538 (Python Code)

Max Activating Token Index: 25

Text #5

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7911. Min Act: -0.0001

Data Index: 1452360 (Python Code)

Max Activating Token Index: 9

Text #6

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7507. Min Act: -0.0001

Data Index: 1454473 (Python Code)

Max Activating Token Index: 96

Text #7

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7498. Min Act: -0.0001

Data Index: 1621049 (Python Code)

Max Activating Token Index: 980

Text #8

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7615. Min Act: -0.0001

Data Index: 1471877 (Python Code)

Max Activating Token Index: 104

Text #9

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7437. Min Act: -0.0001

Data Index: 1558144 (Python Code)

Max Activating Token Index: 479

Text #10

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.8091. Min Act: -0.0001

Data Index: 1580811 (Python Code)

Max Activating Token Index: 57

Text #11

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7762. Min Act: -0.0001

Data Index: 1530126 (Python Code)

Max Activating Token Index: 41

Text #12

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7355. Min Act: -0.0001

Data Index: 1655115 (Python Code)

Max Activating Token Index: 959

Text #13

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7251. Min Act: -0.0001

Data Index: 1444354 (Python Code)

Max Activating Token Index: 15

Text #14

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7492. Min Act: -0.0001

Data Index: 1503783 (Python Code)

Max Activating Token Index: 90

Text #15

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7714. Min Act: -0.0001

Data Index: 1634870 (Python Code)

Max Activating Token Index: 48

Text #16

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.6934. Min Act: -0.0001

Data Index: 1553585 (Python Code)

Max Activating Token Index: 48

Text #17

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7589. Min Act: -0.0001

Data Index: 1473108 (Python Code)

Max Activating Token Index: 404

Text #18

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7981. Min Act: -0.0001

Data Index: 1569602 (Python Code)

Max Activating Token Index: 914

Text #19

Max Range: 0.9098. Min Range: -0.9098

Max Act: 0.7259. Min Act: -0.0001

Data Index: 1502347 (Python Code)

Max Activating Token Index: 21