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

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

Neuron 2962 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0584. Min Range: -2.0584

Max Act: 2.0584. Min Act: -0.0000

Data Index: 1437060 (Python Code)

Max Activating Token Index: 549

Text #1

Max Range: 2.0584. Min Range: -2.0584

Max Act: 1.7752. Min Act: -0.0000

Data Index: 1404160 (Python Code)

Max Activating Token Index: 216

Text #2

Max Range: 2.0584. Min Range: -2.0584

Max Act: 1.4370. Min Act: -0.0000

Data Index: 122036 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 2.0584. Min Range: -2.0584

Max Act: 1.3200. Min Act: -0.0000

Data Index: 1567911 (Python Code)

Max Activating Token Index: 677

Text #4

Max Range: 2.0584. Min Range: -2.0584

Max Act: 1.4467. Min Act: -0.0000

Data Index: 1569525 (Python Code)

Max Activating Token Index: 801

Text #5

Max Range: 2.0584. Min Range: -2.0584

Max Act: 1.3618. Min Act: -0.0000

Data Index: 1495733 (Python Code)

Max Activating Token Index: 254

Text #6

Max Range: 2.0584. Min Range: -2.0584

Max Act: 1.3803. Min Act: -0.0000

Data Index: 1621570 (Python Code)

Max Activating Token Index: 749

Text #7

Max Range: 2.0584. Min Range: -2.0584

Max Act: 1.3517. Min Act: -0.0000

Data Index: 1574525 (Python Code)

Max Activating Token Index: 654

Text #8

Max Range: 2.0584. Min Range: -2.0584

Max Act: 1.3529. Min Act: -0.0000

Data Index: 1483471 (Python Code)

Max Activating Token Index: 562

Text #9

Max Range: 2.0584. Min Range: -2.0584

Max Act: 1.2276. Min Act: -0.0000

Data Index: 1480225 (Python Code)

Max Activating Token Index: 134

Text #10

Max Range: 2.0584. Min Range: -2.0584

Max Act: 1.3259. Min Act: -0.0000

Data Index: 1440955 (Python Code)

Max Activating Token Index: 67

Text #11

Max Range: 2.0584. Min Range: -2.0584

Max Act: 1.3474. Min Act: -0.0000

Data Index: 1415769 (Python Code)

Max Activating Token Index: 243

Text #12

Max Range: 2.0584. Min Range: -2.0584

Max Act: 1.2544. Min Act: -0.0000

Data Index: 1518793 (Python Code)

Max Activating Token Index: 226

Text #13

Max Range: 2.0584. Min Range: -2.0584

Max Act: 1.2823. Min Act: -0.0000

Data Index: 1532285 (Python Code)

Max Activating Token Index: 464

Text #14

Max Range: 2.0584. Min Range: -2.0584

Max Act: 1.2523. Min Act: -0.0000

Data Index: 1452373 (Python Code)

Max Activating Token Index: 688

Text #15

Max Range: 2.0584. Min Range: -2.0584

Max Act: 1.1904. Min Act: -0.0000

Data Index: 1498315 (Python Code)

Max Activating Token Index: 914

Text #16

Max Range: 2.0584. Min Range: -2.0584

Max Act: 1.2688. Min Act: -0.0000

Data Index: 1403814 (Python Code)

Max Activating Token Index: 132

Text #17

Max Range: 2.0584. Min Range: -2.0584

Max Act: 1.2058. Min Act: -0.0000

Data Index: 1514453 (Python Code)

Max Activating Token Index: 1004

Text #18

Max Range: 2.0584. Min Range: -2.0584

Max Act: 1.1981. Min Act: -0.0000

Data Index: 1574307 (Python Code)

Max Activating Token Index: 822

Text #19

Max Range: 2.0584. Min Range: -2.0584

Max Act: 1.2287. Min Act: -0.0000

Data Index: 1396233 (Python Code)

Max Activating Token Index: 955