Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3971 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.4519. Min Range: -3.4519

Max Act: 3.4519. Min Act: -0.0000

Data Index: 1402139 (Python Code)

Max Activating Token Index: 96

Text #1

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.8897. Min Act: -0.0001

Data Index: 1559147 (Python Code)

Max Activating Token Index: 675

Text #2

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.4413. Min Act: -0.0000

Data Index: 1656302 (Python Code)

Max Activating Token Index: 756

Text #3

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.3948. Min Act: -0.0000

Data Index: 1423991 (Python Code)

Max Activating Token Index: 971

Text #4

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.5290. Min Act: -0.0000

Data Index: 1474965 (Python Code)

Max Activating Token Index: 546

Text #5

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.5453. Min Act: -0.0000

Data Index: 1590889 (Python Code)

Max Activating Token Index: 354

Text #6

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.3556. Min Act: -0.0000

Data Index: 1483598 (Python Code)

Max Activating Token Index: 158

Text #7

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.5261. Min Act: -0.0000

Data Index: 1491269 (Python Code)

Max Activating Token Index: 136

Text #8

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.5061. Min Act: -0.0000

Data Index: 1554104 (Python Code)

Max Activating Token Index: 570

Text #9

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.5561. Min Act: -0.0000

Data Index: 1618174 (Python Code)

Max Activating Token Index: 514

Text #10

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.5658. Min Act: -0.0000

Data Index: 1531237 (Python Code)

Max Activating Token Index: 179

Text #11

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.2397. Min Act: -0.0000

Data Index: 1378545 (Python Code)

Max Activating Token Index: 79

Text #12

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.4955. Min Act: -0.0000

Data Index: 1444040 (Python Code)

Max Activating Token Index: 156

Text #13

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.4019. Min Act: -0.0000

Data Index: 1420607 (Python Code)

Max Activating Token Index: 753

Text #14

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.4967. Min Act: -0.0000

Data Index: 1569176 (Python Code)

Max Activating Token Index: 79

Text #15

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.5545. Min Act: -0.0000

Data Index: 1385968 (Python Code)

Max Activating Token Index: 983

Text #16

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.4163. Min Act: -0.0000

Data Index: 1528426 (Python Code)

Max Activating Token Index: 48

Text #17

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.3978. Min Act: -0.0000

Data Index: 1642154 (Python Code)

Max Activating Token Index: 992

Text #18

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.2813. Min Act: -0.0000

Data Index: 1605912 (Python Code)

Max Activating Token Index: 718

Text #19

Max Range: 3.4519. Min Range: -3.4519

Max Act: 2.2630. Min Act: -0.0000

Data Index: 1646711 (Python Code)

Max Activating Token Index: 14