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

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

Neuron 794 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: 0.1030. Min Range: -0.1030

Max Act: 0.1012. Min Act: -0.0000

Data Index: 1656564 (Python Code)

Max Activating Token Index: 91

Text #1

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1390976 (Python Code)

Max Activating Token Index: 521

Text #2

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0973. Min Act: -0.0000

Data Index: 1489538 (Python Code)

Max Activating Token Index: 652

Text #3

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1521210 (Python Code)

Max Activating Token Index: 321

Text #4

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0958. Min Act: 0.0000

Data Index: 1512598 (Python Code)

Max Activating Token Index: 650

Text #5

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0923. Min Act: -0.0000

Data Index: 1379713 (Python Code)

Max Activating Token Index: 147

Text #6

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0840. Min Act: -0.0000

Data Index: 716804 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0866. Min Act: -0.0000

Data Index: 1479255 (Python Code)

Max Activating Token Index: 521

Text #8

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0899. Min Act: -0.0000

Data Index: 1607016 (Python Code)

Max Activating Token Index: 591

Text #9

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1601299 (Python Code)

Max Activating Token Index: 844

Text #10

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1364896 (Python Code)

Max Activating Token Index: 864

Text #11

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0878. Min Act: -0.0000

Data Index: 1645866 (Python Code)

Max Activating Token Index: 133

Text #12

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0867. Min Act: -0.0000

Data Index: 1380262 (Python Code)

Max Activating Token Index: 968

Text #13

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0824. Min Act: -0.0000

Data Index: 1415955 (Python Code)

Max Activating Token Index: 41

Text #14

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0812. Min Act: -0.0000

Data Index: 1475625 (Python Code)

Max Activating Token Index: 770

Text #15

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0840. Min Act: -0.0000

Data Index: 1545523 (Python Code)

Max Activating Token Index: 53

Text #16

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0805. Min Act: -0.0000

Data Index: 651946 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0803. Min Act: -0.0000

Data Index: 1406885 (Python Code)

Max Activating Token Index: 604

Text #18

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0802. Min Act: -0.0000

Data Index: 1580703 (Python Code)

Max Activating Token Index: 566

Text #19

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0795. Min Act: -0.0000

Data Index: 1607838 (Python Code)

Max Activating Token Index: 201