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

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

Neuron 3242 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1245. Min Act: -0.0000

Data Index: 1604466 (Python Code)

Max Activating Token Index: 761

Text #1

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1107. Min Act: -0.0000

Data Index: 695305 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1058. Min Act: -0.0000

Data Index: 375246 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1432471 (Python Code)

Max Activating Token Index: 285

Text #4

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1002. Min Act: -0.0000

Data Index: 1396906 (Python Code)

Max Activating Token Index: 989

Text #5

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1635990 (Python Code)

Max Activating Token Index: 551

Text #6

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1462217 (Python Code)

Max Activating Token Index: 1004

Text #7

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1008. Min Act: -0.0000

Data Index: 1604921 (Python Code)

Max Activating Token Index: 396

Text #8

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1590657 (Python Code)

Max Activating Token Index: 905

Text #9

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0944. Min Act: -0.0000

Data Index: 1560573 (Python Code)

Max Activating Token Index: 136

Text #10

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1412785 (Python Code)

Max Activating Token Index: 671

Text #11

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0876. Min Act: -0.0000

Data Index: 1403414 (Python Code)

Max Activating Token Index: 84

Text #12

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0777. Min Act: -0.0000

Data Index: 1612178 (Python Code)

Max Activating Token Index: 742

Text #13

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0962. Min Act: -0.0000

Data Index: 1484493 (Python Code)

Max Activating Token Index: 916

Text #14

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1576919 (Python Code)

Max Activating Token Index: 571

Text #15

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0838. Min Act: -0.0000

Data Index: 766830 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1497994 (Python Code)

Max Activating Token Index: 90

Text #17

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0867. Min Act: -0.0000

Data Index: 1381593 (Python Code)

Max Activating Token Index: 318

Text #18

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0829. Min Act: -0.0000

Data Index: 1422889 (Python Code)

Max Activating Token Index: 260

Text #19

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0881. Min Act: -0.0000

Data Index: 1496183 (Python Code)

Max Activating Token Index: 97