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

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

Neuron 5636 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: 0.1085. Min Range: -0.1085

Max Act: 0.1085. Min Act: -0.0002

Data Index: 1591961 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.1004. Min Act: -0.0002

Data Index: 1638428 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.1003. Min Act: -0.0002

Data Index: 1461627 (Python Code)

Max Activating Token Index: 925

Text #3

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.1013. Min Act: -0.0002

Data Index: 1508937 (Python Code)

Max Activating Token Index: 12

Text #4

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0985. Min Act: -0.0002

Data Index: 1392566 (Python Code)

Max Activating Token Index: 717

Text #5

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0990. Min Act: -0.0002

Data Index: 1534166 (Python Code)

Max Activating Token Index: 430

Text #6

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0971. Min Act: -0.0002

Data Index: 1485886 (Python Code)

Max Activating Token Index: 217

Text #7

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0982. Min Act: -0.0002

Data Index: 1477241 (Python Code)

Max Activating Token Index: 146

Text #8

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0950. Min Act: -0.0002

Data Index: 1604414 (Python Code)

Max Activating Token Index: 604

Text #9

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0962. Min Act: -0.0002

Data Index: 1496350 (Python Code)

Max Activating Token Index: 389

Text #10

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1536215 (Python Code)

Max Activating Token Index: 74

Text #11

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0933. Min Act: -0.0002

Data Index: 1573740 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0944. Min Act: -0.0002

Data Index: 1479854 (Python Code)

Max Activating Token Index: 581

Text #13

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0945. Min Act: -0.0002

Data Index: 1442161 (Python Code)

Max Activating Token Index: 378

Text #14

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0942. Min Act: -0.0002

Data Index: 1486544 (Python Code)

Max Activating Token Index: 51

Text #15

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0925. Min Act: -0.0002

Data Index: 1563441 (Python Code)

Max Activating Token Index: 925

Text #16

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0928. Min Act: -0.0002

Data Index: 1557424 (Python Code)

Max Activating Token Index: 11

Text #17

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0943. Min Act: -0.0002

Data Index: 1568247 (Python Code)

Max Activating Token Index: 45

Text #18

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0919. Min Act: -0.0002

Data Index: 1529642 (Python Code)

Max Activating Token Index: 139

Text #19

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0949. Min Act: -0.0002

Data Index: 1589331 (Python Code)

Max Activating Token Index: 356