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

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

Neuron 3565 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: 0.1012. Min Range: -0.1012

Max Act: 0.1012. Min Act: -0.0002

Data Index: 1493870 (Python Code)

Max Activating Token Index: 500

Text #1

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0981. Min Act: -0.0002

Data Index: 1419267 (Python Code)

Max Activating Token Index: 841

Text #2

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0984. Min Act: -0.0002

Data Index: 1654141 (Python Code)

Max Activating Token Index: 546

Text #3

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0968. Min Act: -0.0002

Data Index: 1416997 (Python Code)

Max Activating Token Index: 438

Text #4

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0972. Min Act: -0.0002

Data Index: 1656504 (Python Code)

Max Activating Token Index: 128

Text #5

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1463788 (Python Code)

Max Activating Token Index: 43

Text #6

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0951. Min Act: -0.0002

Data Index: 1524157 (Python Code)

Max Activating Token Index: 680

Text #7

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1482121 (Python Code)

Max Activating Token Index: 76

Text #8

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1559007 (Python Code)

Max Activating Token Index: 270

Text #9

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0930. Min Act: -0.0002

Data Index: 1541702 (Python Code)

Max Activating Token Index: 373

Text #10

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1432800 (Python Code)

Max Activating Token Index: 661

Text #11

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0944. Min Act: -0.0002

Data Index: 1502325 (Python Code)

Max Activating Token Index: 25

Text #12

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0943. Min Act: -0.0002

Data Index: 1647988 (Python Code)

Max Activating Token Index: 77

Text #13

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0928. Min Act: -0.0002

Data Index: 1553381 (Python Code)

Max Activating Token Index: 601

Text #14

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0921. Min Act: -0.0002

Data Index: 1523070 (Python Code)

Max Activating Token Index: 130

Text #15

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0907. Min Act: -0.0002

Data Index: 1467417 (Python Code)

Max Activating Token Index: 619

Text #16

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0923. Min Act: -0.0002

Data Index: 1591674 (Python Code)

Max Activating Token Index: 77

Text #17

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0911. Min Act: -0.0002

Data Index: 1528672 (Python Code)

Max Activating Token Index: 194

Text #18

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0919. Min Act: -0.0002

Data Index: 1424730 (Python Code)

Max Activating Token Index: 99

Text #19

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0909. Min Act: -0.0002

Data Index: 1398920 (Python Code)

Max Activating Token Index: 66