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

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

Neuron 5708 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1664. Min Range: -4.1664

Max Act: 4.1664. Min Act: -0.0000

Data Index: 1408007 (Python Code)

Max Activating Token Index: 227

Text #1

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.9650. Min Act: -0.0000

Data Index: 1584047 (Python Code)

Max Activating Token Index: 65

Text #2

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.8564. Min Act: -0.0000

Data Index: 1511485 (Python Code)

Max Activating Token Index: 326

Text #3

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.8082. Min Act: -0.0000

Data Index: 1634478 (Python Code)

Max Activating Token Index: 428

Text #4

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.7776. Min Act: -0.0000

Data Index: 1500137 (Python Code)

Max Activating Token Index: 284

Text #5

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.3762. Min Act: -0.0000

Data Index: 1517560 (Python Code)

Max Activating Token Index: 365

Text #6

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.4111. Min Act: -0.0000

Data Index: 1596488 (Python Code)

Max Activating Token Index: 614

Text #7

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.0694. Min Act: -0.0000

Data Index: 1557478 (Python Code)

Max Activating Token Index: 511

Text #8

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.1950. Min Act: -0.0000

Data Index: 1477254 (Python Code)

Max Activating Token Index: 578

Text #9

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.1124. Min Act: -0.0000

Data Index: 1427661 (Python Code)

Max Activating Token Index: 635

Text #10

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.2550. Min Act: -0.0000

Data Index: 1562180 (Python Code)

Max Activating Token Index: 980

Text #11

Max Range: 4.1664. Min Range: -4.1664

Max Act: 2.9439. Min Act: -0.0000

Data Index: 1442186 (Python Code)

Max Activating Token Index: 774

Text #12

Max Range: 4.1664. Min Range: -4.1664

Max Act: 3.2076. Min Act: -0.0000

Data Index: 1553969 (Python Code)

Max Activating Token Index: 772

Text #13

Max Range: 4.1664. Min Range: -4.1664

Max Act: 2.9895. Min Act: -0.0000

Data Index: 1532563 (Python Code)

Max Activating Token Index: 447

Text #14

Max Range: 4.1664. Min Range: -4.1664

Max Act: 2.7946. Min Act: -0.0000

Data Index: 1458455 (Python Code)

Max Activating Token Index: 984

Text #15

Max Range: 4.1664. Min Range: -4.1664

Max Act: 2.8875. Min Act: -0.0000

Data Index: 1368705 (Python Code)

Max Activating Token Index: 673

Text #16

Max Range: 4.1664. Min Range: -4.1664

Max Act: 2.8744. Min Act: -0.0000

Data Index: 1475630 (Python Code)

Max Activating Token Index: 307

Text #17

Max Range: 4.1664. Min Range: -4.1664

Max Act: 2.8610. Min Act: -0.0000

Data Index: 1528504 (Python Code)

Max Activating Token Index: 649

Text #18

Max Range: 4.1664. Min Range: -4.1664

Max Act: 2.8504. Min Act: -0.0000

Data Index: 1384168 (Python Code)

Max Activating Token Index: 967

Text #19

Max Range: 4.1664. Min Range: -4.1664

Max Act: 2.6828. Min Act: -0.0000

Data Index: 1368290 (Python Code)

Max Activating Token Index: 859