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

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

Neuron 1555 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: 4.5806. Min Range: -4.5806

Max Act: 4.5806. Min Act: -0.0000

Data Index: 1378183 (Python Code)

Max Activating Token Index: 449

Text #1

Max Range: 4.5806. Min Range: -4.5806

Max Act: 4.2533. Min Act: -0.0000

Data Index: 1476503 (Python Code)

Max Activating Token Index: 511

Text #2

Max Range: 4.5806. Min Range: -4.5806

Max Act: 3.8691. Min Act: -0.0000

Data Index: 1387331 (Python Code)

Max Activating Token Index: 837

Text #3

Max Range: 4.5806. Min Range: -4.5806

Max Act: 3.6819. Min Act: -0.0000

Data Index: 1521463 (Python Code)

Max Activating Token Index: 923

Text #4

Max Range: 4.5806. Min Range: -4.5806

Max Act: 3.9893. Min Act: -0.0000

Data Index: 1606613 (Python Code)

Max Activating Token Index: 325

Text #5

Max Range: 4.5806. Min Range: -4.5806

Max Act: 3.7926. Min Act: -0.0000

Data Index: 1547705 (Python Code)

Max Activating Token Index: 168

Text #6

Max Range: 4.5806. Min Range: -4.5806

Max Act: 3.8085. Min Act: -0.0001

Data Index: 1552550 (Python Code)

Max Activating Token Index: 887

Text #7

Max Range: 4.5806. Min Range: -4.5806

Max Act: 3.7585. Min Act: -0.0000

Data Index: 1451660 (Python Code)

Max Activating Token Index: 453

Text #8

Max Range: 4.5806. Min Range: -4.5806

Max Act: 3.5505. Min Act: -0.0000

Data Index: 1411908 (Python Code)

Max Activating Token Index: 679

Text #9

Max Range: 4.5806. Min Range: -4.5806

Max Act: 3.5528. Min Act: -0.0000

Data Index: 1598276 (Python Code)

Max Activating Token Index: 636

Text #10

Max Range: 4.5806. Min Range: -4.5806

Max Act: 3.4697. Min Act: -0.0000

Data Index: 1555903 (Python Code)

Max Activating Token Index: 517

Text #11

Max Range: 4.5806. Min Range: -4.5806

Max Act: 3.4240. Min Act: -0.0000

Data Index: 1432254 (Python Code)

Max Activating Token Index: 972

Text #12

Max Range: 4.5806. Min Range: -4.5806

Max Act: 3.5728. Min Act: -0.0000

Data Index: 1478476 (Python Code)

Max Activating Token Index: 735

Text #13

Max Range: 4.5806. Min Range: -4.5806

Max Act: 3.5709. Min Act: -0.0000

Data Index: 1418139 (Python Code)

Max Activating Token Index: 512

Text #14

Max Range: 4.5806. Min Range: -4.5806

Max Act: 3.3900. Min Act: -0.0000

Data Index: 1465946 (Python Code)

Max Activating Token Index: 531

Text #15

Max Range: 4.5806. Min Range: -4.5806

Max Act: 3.6423. Min Act: -0.0000

Data Index: 1547230 (Python Code)

Max Activating Token Index: 879

Text #16

Max Range: 4.5806. Min Range: -4.5806

Max Act: 3.4687. Min Act: -0.0000

Data Index: 1615958 (Python Code)

Max Activating Token Index: 436

Text #17

Max Range: 4.5806. Min Range: -4.5806

Max Act: 3.4789. Min Act: -0.0000

Data Index: 1399671 (Python Code)

Max Activating Token Index: 717

Text #18

Max Range: 4.5806. Min Range: -4.5806

Max Act: 3.2614. Min Act: -0.0000

Data Index: 1476543 (Python Code)

Max Activating Token Index: 305

Text #19

Max Range: 4.5806. Min Range: -4.5806

Max Act: 3.3949. Min Act: -0.0000

Data Index: 1431585 (Python Code)

Max Activating Token Index: 751