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

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

Neuron 390 in Layer 0

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: 0.1923. Min Range: -0.1923

Max Act: 0.1923. Min Act: -0.0001

Data Index: 449507 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1866. Min Act: -0.0001

Data Index: 976057 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1876. Min Act: -0.0001

Data Index: 912154 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1825. Min Act: -0.0001

Data Index: 1038133 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1842. Min Act: -0.0001

Data Index: 703273 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1801. Min Act: -0.0001

Data Index: 342836 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1787. Min Act: -0.0001

Data Index: 35988 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1802. Min Act: -0.0001

Data Index: 69276 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1826. Min Act: -0.0001

Data Index: 815141 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1796. Min Act: -0.0001

Data Index: 689938 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1789. Min Act: -0.0001

Data Index: 780125 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1764. Min Act: -0.0001

Data Index: 266117 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1781. Min Act: -0.0001

Data Index: 263533 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1744. Min Act: -0.0001

Data Index: 296815 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1713. Min Act: -0.0001

Data Index: 658119 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1738. Min Act: -0.0001

Data Index: 633070 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1731. Min Act: -0.0001

Data Index: 687112 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1707. Min Act: -0.0001

Data Index: 521838 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1754. Min Act: -0.0002

Data Index: 897612 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1685. Min Act: -0.0001

Data Index: 940170 (C4 (Web Text))

Max Activating Token Index: 611