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

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

Neuron 3521 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: 0.5670. Min Range: -0.5670

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1644677 (Python Code)

Max Activating Token Index: 639

Text #1

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.4612. Min Act: -0.0000

Data Index: 1651054 (Python Code)

Max Activating Token Index: 356

Text #2

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.4761. Min Act: -0.0000

Data Index: 1406440 (Python Code)

Max Activating Token Index: 106

Text #3

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1447665 (Python Code)

Max Activating Token Index: 117

Text #4

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1363371 (Python Code)

Max Activating Token Index: 143

Text #5

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1563520 (Python Code)

Max Activating Token Index: 167

Text #6

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1372709 (Python Code)

Max Activating Token Index: 981

Text #7

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3595. Min Act: -0.0000

Data Index: 1620013 (Python Code)

Max Activating Token Index: 819

Text #8

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1447022 (Python Code)

Max Activating Token Index: 399

Text #9

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1633688 (Python Code)

Max Activating Token Index: 391

Text #10

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3725. Min Act: -0.0000

Data Index: 1602853 (Python Code)

Max Activating Token Index: 217

Text #11

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3558. Min Act: -0.0000

Data Index: 1645819 (Python Code)

Max Activating Token Index: 356

Text #12

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3435. Min Act: -0.0000

Data Index: 1437583 (Python Code)

Max Activating Token Index: 370

Text #13

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3599. Min Act: -0.0000

Data Index: 1450299 (Python Code)

Max Activating Token Index: 455

Text #14

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3693. Min Act: -0.0000

Data Index: 1616861 (Python Code)

Max Activating Token Index: 11

Text #15

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3580. Min Act: -0.0000

Data Index: 1476321 (Python Code)

Max Activating Token Index: 1004

Text #16

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3525. Min Act: -0.0000

Data Index: 1609873 (Python Code)

Max Activating Token Index: 79

Text #17

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3832. Min Act: -0.0000

Data Index: 1484176 (Python Code)

Max Activating Token Index: 349

Text #18

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3339. Min Act: -0.0000

Data Index: 1616004 (Python Code)

Max Activating Token Index: 996

Text #19

Max Range: 0.5670. Min Range: -0.5670

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1412938 (Python Code)

Max Activating Token Index: 189