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

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

Neuron 192 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.4396. Min Act: -0.0000

Data Index: 1566873 (Python Code)

Max Activating Token Index: 48

Text #1

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.4967. Min Act: 0.0000

Data Index: 1482650 (Python Code)

Max Activating Token Index: 1012

Text #2

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.4318. Min Act: -0.0000

Data Index: 1537148 (Python Code)

Max Activating Token Index: 88

Text #3

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.3031. Min Act: 0.0000

Data Index: 1422053 (Python Code)

Max Activating Token Index: 65

Text #4

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.3051. Min Act: -0.0000

Data Index: 1634512 (Python Code)

Max Activating Token Index: 920

Text #5

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.3418. Min Act: -0.0000

Data Index: 1462255 (Python Code)

Max Activating Token Index: 64

Text #6

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.2678. Min Act: -0.0000

Data Index: 1564468 (Python Code)

Max Activating Token Index: 910

Text #7

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.1699. Min Act: -0.0000

Data Index: 1560074 (Python Code)

Max Activating Token Index: 942

Text #8

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.1530. Min Act: -0.0000

Data Index: 1608815 (Python Code)

Max Activating Token Index: 969

Text #9

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.0990. Min Act: -0.0000

Data Index: 1563708 (Python Code)

Max Activating Token Index: 370

Text #10

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.1543. Min Act: -0.0000

Data Index: 1533761 (Python Code)

Max Activating Token Index: 507

Text #11

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.0965. Min Act: -0.0000

Data Index: 1496486 (Python Code)

Max Activating Token Index: 435

Text #12

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.1397. Min Act: -0.0000

Data Index: 1630626 (Python Code)

Max Activating Token Index: 875

Text #13

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.1229. Min Act: -0.0000

Data Index: 1378394 (Python Code)

Max Activating Token Index: 292

Text #14

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.0561. Min Act: -0.0000

Data Index: 1440398 (Python Code)

Max Activating Token Index: 944

Text #15

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.0902. Min Act: -0.0000

Data Index: 1464652 (Python Code)

Max Activating Token Index: 404

Text #16

Max Range: 1.4967. Min Range: -1.4967

Max Act: 0.9906. Min Act: -0.0000

Data Index: 1570053 (Python Code)

Max Activating Token Index: 729

Text #17

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.1078. Min Act: -0.0000

Data Index: 1475160 (Python Code)

Max Activating Token Index: 68

Text #18

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.0513. Min Act: 0.0000

Data Index: 1551741 (Python Code)

Max Activating Token Index: 624

Text #19

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.0531. Min Act: -0.0000

Data Index: 1443370 (Python Code)

Max Activating Token Index: 612