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

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

Neuron 5621 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.3757. Min Act: -0.0000

Data Index: 1453987 (Python Code)

Max Activating Token Index: 387

Text #1

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.4649. Min Act: -0.0000

Data Index: 1449145 (Python Code)

Max Activating Token Index: 375

Text #2

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.2269. Min Act: -0.0000

Data Index: 1421673 (Python Code)

Max Activating Token Index: 234

Text #3

Max Range: 4.4649. Min Range: -4.4649

Max Act: 3.8648. Min Act: -0.0000

Data Index: 1476947 (Python Code)

Max Activating Token Index: 1016

Text #4

Max Range: 4.4649. Min Range: -4.4649

Max Act: 3.9135. Min Act: -0.0000

Data Index: 1471848 (Python Code)

Max Activating Token Index: 655

Text #5

Max Range: 4.4649. Min Range: -4.4649

Max Act: 3.9145. Min Act: -0.0000

Data Index: 1520427 (Python Code)

Max Activating Token Index: 512

Text #6

Max Range: 4.4649. Min Range: -4.4649

Max Act: 3.7681. Min Act: -0.0000

Data Index: 1483635 (Python Code)

Max Activating Token Index: 64

Text #7

Max Range: 4.4649. Min Range: -4.4649

Max Act: 3.7478. Min Act: -0.0000

Data Index: 1423334 (Python Code)

Max Activating Token Index: 497

Text #8

Max Range: 4.4649. Min Range: -4.4649

Max Act: 3.5027. Min Act: -0.0000

Data Index: 1578512 (Python Code)

Max Activating Token Index: 560

Text #9

Max Range: 4.4649. Min Range: -4.4649

Max Act: 3.3797. Min Act: -0.0000

Data Index: 1436953 (Python Code)

Max Activating Token Index: 644

Text #10

Max Range: 4.4649. Min Range: -4.4649

Max Act: 3.3988. Min Act: -0.0000

Data Index: 1371248 (Python Code)

Max Activating Token Index: 565

Text #11

Max Range: 4.4649. Min Range: -4.4649

Max Act: 3.4613. Min Act: -0.0000

Data Index: 1578792 (Python Code)

Max Activating Token Index: 494

Text #12

Max Range: 4.4649. Min Range: -4.4649

Max Act: 3.0896. Min Act: -0.0000

Data Index: 1395719 (Python Code)

Max Activating Token Index: 220

Text #13

Max Range: 4.4649. Min Range: -4.4649

Max Act: 3.2169. Min Act: -0.0000

Data Index: 514062 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 4.4649. Min Range: -4.4649

Max Act: 3.1390. Min Act: -0.0000

Data Index: 1640347 (Python Code)

Max Activating Token Index: 195

Text #15

Max Range: 4.4649. Min Range: -4.4649

Max Act: 3.1460. Min Act: -0.0000

Data Index: 1397721 (Python Code)

Max Activating Token Index: 1005

Text #16

Max Range: 4.4649. Min Range: -4.4649

Max Act: 2.9885. Min Act: -0.0000

Data Index: 1414359 (Python Code)

Max Activating Token Index: 563

Text #17

Max Range: 4.4649. Min Range: -4.4649

Max Act: 2.9946. Min Act: -0.0000

Data Index: 1603322 (Python Code)

Max Activating Token Index: 954

Text #18

Max Range: 4.4649. Min Range: -4.4649

Max Act: 3.0998. Min Act: -0.0000

Data Index: 1379221 (Python Code)

Max Activating Token Index: 571

Text #19

Max Range: 4.4649. Min Range: -4.4649

Max Act: 2.9578. Min Act: -0.0000

Data Index: 1347002 (C4 (Web Text))

Max Activating Token Index: 705