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

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

Neuron 3228 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0892. Min Act: -0.0001

Data Index: 1447359 (Python Code)

Max Activating Token Index: 122

Text #1

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0726. Min Act: -0.0000

Data Index: 1612768 (Python Code)

Max Activating Token Index: 1013

Text #2

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0667. Min Act: -0.0001

Data Index: 1492293 (Python Code)

Max Activating Token Index: 816

Text #3

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0731. Min Act: -0.0001

Data Index: 1503015 (Python Code)

Max Activating Token Index: 55

Text #4

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0676. Min Act: -0.0001

Data Index: 1394578 (Python Code)

Max Activating Token Index: 173

Text #5

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0670. Min Act: -0.0001

Data Index: 1551584 (Python Code)

Max Activating Token Index: 296

Text #6

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1447613 (Python Code)

Max Activating Token Index: 301

Text #7

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0646. Min Act: -0.0001

Data Index: 244061 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0612. Min Act: -0.0001

Data Index: 1380906 (Python Code)

Max Activating Token Index: 764

Text #9

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0626. Min Act: -0.0001

Data Index: 1625824 (Python Code)

Max Activating Token Index: 60

Text #10

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1521087 (Python Code)

Max Activating Token Index: 751

Text #11

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0630. Min Act: -0.0000

Data Index: 1489558 (Python Code)

Max Activating Token Index: 135

Text #12

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0626. Min Act: -0.0001

Data Index: 242499 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0640. Min Act: -0.0000

Data Index: 1656374 (Python Code)

Max Activating Token Index: 79

Text #14

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0617. Min Act: -0.0001

Data Index: 1394752 (Python Code)

Max Activating Token Index: 552

Text #15

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1495152 (Python Code)

Max Activating Token Index: 625

Text #16

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1651967 (Python Code)

Max Activating Token Index: 833

Text #17

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0609. Min Act: -0.0001

Data Index: 1625340 (Python Code)

Max Activating Token Index: 102

Text #18

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0585. Min Act: -0.0000

Data Index: 1507671 (Python Code)

Max Activating Token Index: 136

Text #19

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1589416 (Python Code)

Max Activating Token Index: 344