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

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

Neuron 3649 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: 0.1026. Min Range: -0.1026

Max Act: 0.1026. Min Act: -0.0002

Data Index: 1627032 (Python Code)

Max Activating Token Index: 1016

Text #1

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.1015. Min Act: -0.0002

Data Index: 1367581 (Python Code)

Max Activating Token Index: 447

Text #2

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.1005. Min Act: -0.0002

Data Index: 1656414 (Python Code)

Max Activating Token Index: 274

Text #3

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.1006. Min Act: -0.0002

Data Index: 1573158 (Python Code)

Max Activating Token Index: 724

Text #4

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0980. Min Act: -0.0002

Data Index: 1618595 (Python Code)

Max Activating Token Index: 11

Text #5

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1639055 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1445907 (Python Code)

Max Activating Token Index: 196

Text #7

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0928. Min Act: -0.0002

Data Index: 1405411 (Python Code)

Max Activating Token Index: 960

Text #8

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0935. Min Act: -0.0002

Data Index: 1603963 (Python Code)

Max Activating Token Index: 642

Text #9

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0904. Min Act: -0.0002

Data Index: 1585643 (Python Code)

Max Activating Token Index: 297

Text #10

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0924. Min Act: -0.0002

Data Index: 1533882 (Python Code)

Max Activating Token Index: 634

Text #11

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1532314 (Python Code)

Max Activating Token Index: 28

Text #12

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0890. Min Act: -0.0002

Data Index: 1581554 (Python Code)

Max Activating Token Index: 490

Text #13

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0897. Min Act: -0.0002

Data Index: 1378323 (Python Code)

Max Activating Token Index: 565

Text #14

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0906. Min Act: -0.0002

Data Index: 1646084 (Python Code)

Max Activating Token Index: 866

Text #15

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0918. Min Act: -0.0002

Data Index: 1391185 (Python Code)

Max Activating Token Index: 780

Text #16

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0895. Min Act: -0.0002

Data Index: 1527050 (Python Code)

Max Activating Token Index: 461

Text #17

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0910. Min Act: -0.0002

Data Index: 1553107 (Python Code)

Max Activating Token Index: 630

Text #18

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0866. Min Act: -0.0002

Data Index: 1535816 (Python Code)

Max Activating Token Index: 147

Text #19

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0872. Min Act: -0.0002

Data Index: 1530707 (Python Code)

Max Activating Token Index: 270