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

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

Neuron 2803 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 7.5392. Min Range: -7.5392

Max Act: 7.5392. Min Act: -0.0000

Data Index: 1608966 (Python Code)

Max Activating Token Index: 997

Text #1

Max Range: 7.5392. Min Range: -7.5392

Max Act: 7.3140. Min Act: -0.0000

Data Index: 1561055 (Python Code)

Max Activating Token Index: 70

Text #2

Max Range: 7.5392. Min Range: -7.5392

Max Act: 6.5498. Min Act: -0.0000

Data Index: 1406556 (Python Code)

Max Activating Token Index: 581

Text #3

Max Range: 7.5392. Min Range: -7.5392

Max Act: 6.3929. Min Act: -0.0000

Data Index: 1502871 (Python Code)

Max Activating Token Index: 44

Text #4

Max Range: 7.5392. Min Range: -7.5392

Max Act: 6.7309. Min Act: -0.0000

Data Index: 1612537 (Python Code)

Max Activating Token Index: 757

Text #5

Max Range: 7.5392. Min Range: -7.5392

Max Act: 6.4814. Min Act: -0.0000

Data Index: 1635545 (Python Code)

Max Activating Token Index: 29

Text #6

Max Range: 7.5392. Min Range: -7.5392

Max Act: 6.6319. Min Act: -0.0000

Data Index: 1429503 (Python Code)

Max Activating Token Index: 730

Text #7

Max Range: 7.5392. Min Range: -7.5392

Max Act: 6.4502. Min Act: -0.0000

Data Index: 1380704 (Python Code)

Max Activating Token Index: 580

Text #8

Max Range: 7.5392. Min Range: -7.5392

Max Act: 6.4174. Min Act: -0.0000

Data Index: 1456348 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 7.5392. Min Range: -7.5392

Max Act: 6.1754. Min Act: -0.0000

Data Index: 1475470 (Python Code)

Max Activating Token Index: 506

Text #10

Max Range: 7.5392. Min Range: -7.5392

Max Act: 6.1407. Min Act: -0.0000

Data Index: 1384000 (Python Code)

Max Activating Token Index: 472

Text #11

Max Range: 7.5392. Min Range: -7.5392

Max Act: 6.3147. Min Act: -0.0000

Data Index: 1545517 (Python Code)

Max Activating Token Index: 24

Text #12

Max Range: 7.5392. Min Range: -7.5392

Max Act: 6.3247. Min Act: -0.0000

Data Index: 1526303 (Python Code)

Max Activating Token Index: 36

Text #13

Max Range: 7.5392. Min Range: -7.5392

Max Act: 6.5097. Min Act: -0.0000

Data Index: 1534581 (Python Code)

Max Activating Token Index: 113

Text #14

Max Range: 7.5392. Min Range: -7.5392

Max Act: 6.4702. Min Act: -0.0000

Data Index: 1505256 (Python Code)

Max Activating Token Index: 498

Text #15

Max Range: 7.5392. Min Range: -7.5392

Max Act: 6.0984. Min Act: -0.0000

Data Index: 1504050 (Python Code)

Max Activating Token Index: 947

Text #16

Max Range: 7.5392. Min Range: -7.5392

Max Act: 6.0990. Min Act: -0.0000

Data Index: 1489998 (Python Code)

Max Activating Token Index: 73

Text #17

Max Range: 7.5392. Min Range: -7.5392

Max Act: 6.2430. Min Act: -0.0000

Data Index: 1470903 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 7.5392. Min Range: -7.5392

Max Act: 6.2516. Min Act: -0.0000

Data Index: 1370801 (Python Code)

Max Activating Token Index: 170

Text #19

Max Range: 7.5392. Min Range: -7.5392

Max Act: 6.2284. Min Act: -0.0000

Data Index: 1377630 (Python Code)

Max Activating Token Index: 260