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

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

Neuron 4369 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: 0.1700. Min Range: -0.1700

Max Act: 0.1658. Min Act: -0.0000

Data Index: 1570229 (Python Code)

Max Activating Token Index: 291

Text #1

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1700. Min Act: -0.0001

Data Index: 1450434 (Python Code)

Max Activating Token Index: 567

Text #2

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1641. Min Act: -0.0001

Data Index: 1597207 (Python Code)

Max Activating Token Index: 44

Text #3

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1270. Min Act: -0.0000

Data Index: 1553299 (Python Code)

Max Activating Token Index: 232

Text #4

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1061. Min Act: -0.0000

Data Index: 1362085 (Python Code)

Max Activating Token Index: 123

Text #5

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.0977. Min Act: -0.0001

Data Index: 1558733 (Python Code)

Max Activating Token Index: 1019

Text #6

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.0930. Min Act: -0.0001

Data Index: 805418 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1190287 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1041564 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.0881. Min Act: -0.0000

Data Index: 1650894 (Python Code)

Max Activating Token Index: 639

Text #10

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.0929. Min Act: -0.0001

Data Index: 797573 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1645466 (Python Code)

Max Activating Token Index: 555

Text #12

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1504498 (Python Code)

Max Activating Token Index: 212

Text #13

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1547554 (Python Code)

Max Activating Token Index: 434

Text #14

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.0869. Min Act: -0.0001

Data Index: 713522 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.0896. Min Act: -0.0001

Data Index: 959237 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.0896. Min Act: -0.0001

Data Index: 1540498 (Python Code)

Max Activating Token Index: 940

Text #17

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.0848. Min Act: -0.0000

Data Index: 1505363 (Python Code)

Max Activating Token Index: 194

Text #18

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.0814. Min Act: -0.0000

Data Index: 1454111 (Python Code)

Max Activating Token Index: 744

Text #19

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.0835. Min Act: -0.0000

Data Index: 1628854 (Python Code)

Max Activating Token Index: 179