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

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

Neuron 360 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1987. Min Act: -0.0002

Data Index: 1154135 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1913. Min Act: -0.0002

Data Index: 1433243 (Python Code)

Max Activating Token Index: 228

Text #2

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1938. Min Act: -0.0002

Data Index: 1557602 (Python Code)

Max Activating Token Index: 36

Text #3

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1928. Min Act: -0.0002

Data Index: 1604768 (Python Code)

Max Activating Token Index: 42

Text #4

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1937. Min Act: -0.0002

Data Index: 1652975 (Python Code)

Max Activating Token Index: 21

Text #5

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1874. Min Act: -0.0002

Data Index: 1544015 (Python Code)

Max Activating Token Index: 51

Text #6

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1828. Min Act: -0.0002

Data Index: 1550154 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1790. Min Act: -0.0002

Data Index: 1623146 (Python Code)

Max Activating Token Index: 60

Text #8

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1835. Min Act: -0.0002

Data Index: 1536188 (Python Code)

Max Activating Token Index: 62

Text #9

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1788. Min Act: -0.0002

Data Index: 1519463 (Python Code)

Max Activating Token Index: 371

Text #10

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1803. Min Act: -0.0002

Data Index: 1539817 (Python Code)

Max Activating Token Index: 304

Text #11

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1805. Min Act: -0.0002

Data Index: 1407700 (Python Code)

Max Activating Token Index: 38

Text #12

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1795. Min Act: -0.0002

Data Index: 1400515 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1763. Min Act: -0.0002

Data Index: 1327306 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1806. Min Act: -0.0002

Data Index: 1474308 (Python Code)

Max Activating Token Index: 935

Text #15

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1762. Min Act: -0.0002

Data Index: 1469840 (Python Code)

Max Activating Token Index: 502

Text #16

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1808. Min Act: -0.0002

Data Index: 1459555 (Python Code)

Max Activating Token Index: 113

Text #17

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1810. Min Act: -0.0002

Data Index: 1501324 (Python Code)

Max Activating Token Index: 22

Text #18

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1799. Min Act: -0.0002

Data Index: 1499368 (Python Code)

Max Activating Token Index: 55

Text #19

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1788. Min Act: -0.0002

Data Index: 1461870 (Python Code)

Max Activating Token Index: 24