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

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

Neuron 3817 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9890. Min Range: -1.9890

Max Act: 1.9767. Min Act: 0.0001

Data Index: 1396160 (Python Code)

Max Activating Token Index: 271

Text #1

Max Range: 1.9890. Min Range: -1.9890

Max Act: 1.9890. Min Act: 0.0000

Data Index: 1646662 (Python Code)

Max Activating Token Index: 247

Text #2

Max Range: 1.9890. Min Range: -1.9890

Max Act: 1.8354. Min Act: -0.0000

Data Index: 1443913 (Python Code)

Max Activating Token Index: 919

Text #3

Max Range: 1.9890. Min Range: -1.9890

Max Act: 1.9240. Min Act: 0.0001

Data Index: 1655243 (Python Code)

Max Activating Token Index: 151

Text #4

Max Range: 1.9890. Min Range: -1.9890

Max Act: 1.8502. Min Act: 0.0001

Data Index: 1545619 (Python Code)

Max Activating Token Index: 232

Text #5

Max Range: 1.9890. Min Range: -1.9890

Max Act: 1.8900. Min Act: 0.0001

Data Index: 1547835 (Python Code)

Max Activating Token Index: 591

Text #6

Max Range: 1.9890. Min Range: -1.9890

Max Act: 1.8041. Min Act: 0.0001

Data Index: 1587273 (Python Code)

Max Activating Token Index: 605

Text #7

Max Range: 1.9890. Min Range: -1.9890

Max Act: 1.8866. Min Act: -0.0000

Data Index: 1411863 (Python Code)

Max Activating Token Index: 271

Text #8

Max Range: 1.9890. Min Range: -1.9890

Max Act: 1.8826. Min Act: 0.0001

Data Index: 1478134 (Python Code)

Max Activating Token Index: 392

Text #9

Max Range: 1.9890. Min Range: -1.9890

Max Act: 1.8758. Min Act: 0.0001

Data Index: 1464465 (Python Code)

Max Activating Token Index: 451

Text #10

Max Range: 1.9890. Min Range: -1.9890

Max Act: 1.8718. Min Act: 0.0001

Data Index: 1420349 (Python Code)

Max Activating Token Index: 353

Text #11

Max Range: 1.9890. Min Range: -1.9890

Max Act: 1.9741. Min Act: 0.0001

Data Index: 1474313 (Python Code)

Max Activating Token Index: 97

Text #12

Max Range: 1.9890. Min Range: -1.9890

Max Act: 1.7043. Min Act: 0.0000

Data Index: 1469417 (Python Code)

Max Activating Token Index: 482

Text #13

Max Range: 1.9890. Min Range: -1.9890

Max Act: 1.7932. Min Act: 0.0001

Data Index: 1469081 (Python Code)

Max Activating Token Index: 635

Text #14

Max Range: 1.9890. Min Range: -1.9890

Max Act: 1.7879. Min Act: 0.0001

Data Index: 1424236 (Python Code)

Max Activating Token Index: 796

Text #15

Max Range: 1.9890. Min Range: -1.9890

Max Act: 1.7869. Min Act: 0.0001

Data Index: 1436789 (Python Code)

Max Activating Token Index: 748

Text #16

Max Range: 1.9890. Min Range: -1.9890

Max Act: 1.7677. Min Act: 0.0001

Data Index: 1400289 (Python Code)

Max Activating Token Index: 754

Text #17

Max Range: 1.9890. Min Range: -1.9890

Max Act: 1.6651. Min Act: 0.0001

Data Index: 1498421 (Python Code)

Max Activating Token Index: 975

Text #18

Max Range: 1.9890. Min Range: -1.9890

Max Act: 1.6688. Min Act: 0.0001

Data Index: 1378669 (Python Code)

Max Activating Token Index: 772

Text #19

Max Range: 1.9890. Min Range: -1.9890

Max Act: 1.7307. Min Act: 0.0000

Data Index: 1513918 (Python Code)

Max Activating Token Index: 476