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

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

Neuron 3224 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: 0.2014. Min Range: -0.2014

Max Act: 0.2014. Min Act: -0.0002

Data Index: 576943 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1986. Min Act: -0.0002

Data Index: 782532 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1984. Min Act: -0.0002

Data Index: 957901 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1926. Min Act: -0.0002

Data Index: 652070 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1906. Min Act: -0.0002

Data Index: 1097595 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1882. Min Act: -0.0002

Data Index: 602668 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1880. Min Act: -0.0002

Data Index: 661269 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1899. Min Act: -0.0002

Data Index: 178899 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1897. Min Act: -0.0002

Data Index: 944868 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1887. Min Act: -0.0002

Data Index: 860562 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1880. Min Act: -0.0002

Data Index: 1179341 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1883. Min Act: -0.0002

Data Index: 768930 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1859. Min Act: -0.0002

Data Index: 1353199 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1876. Min Act: -0.0002

Data Index: 1316677 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1877. Min Act: -0.0002

Data Index: 1124025 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1835. Min Act: -0.0002

Data Index: 701366 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1868. Min Act: -0.0002

Data Index: 590606 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1839. Min Act: -0.0002

Data Index: 1326026 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1874. Min Act: -0.0002

Data Index: 532044 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.2014. Min Range: -0.2014

Max Act: 0.1835. Min Act: -0.0002

Data Index: 1156155 (C4 (Web Text))

Max Activating Token Index: 810