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

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

Neuron 427 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1371816 (Python Code)

Max Activating Token Index: 1

Text #1

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1385149 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1390074 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1429098 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1436617 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1557668 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1634761 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1369889 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1642176 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1409750 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1359932 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1360331 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1360694 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1360550 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1360587 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1360756 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1360540 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1360011 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1360721 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1359903 (Python Code)

Max Activating Token Index: 1