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

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

Neuron 3977 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.9987. Min Act: -0.0000

Data Index: 1629530 (Python Code)

Max Activating Token Index: 455

Text #1

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.9314. Min Act: -0.0000

Data Index: 1412065 (Python Code)

Max Activating Token Index: 375

Text #2

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.8097. Min Act: -0.0000

Data Index: 1537510 (Python Code)

Max Activating Token Index: 558

Text #3

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.8367. Min Act: -0.0000

Data Index: 1423560 (Python Code)

Max Activating Token Index: 27

Text #4

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1655432 (Python Code)

Max Activating Token Index: 74

Text #5

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.7938. Min Act: -0.0000

Data Index: 1642158 (Python Code)

Max Activating Token Index: 1009

Text #6

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.7892. Min Act: -0.0000

Data Index: 1373727 (Python Code)

Max Activating Token Index: 593

Text #7

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.7122. Min Act: -0.0000

Data Index: 1364432 (Python Code)

Max Activating Token Index: 965

Text #8

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1479933 (Python Code)

Max Activating Token Index: 37

Text #9

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.6819. Min Act: -0.0000

Data Index: 1568086 (Python Code)

Max Activating Token Index: 766

Text #10

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.7352. Min Act: -0.0000

Data Index: 1643589 (Python Code)

Max Activating Token Index: 25

Text #11

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.6901. Min Act: -0.0000

Data Index: 1447370 (Python Code)

Max Activating Token Index: 12

Text #12

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.6890. Min Act: -0.0000

Data Index: 1438345 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.6878. Min Act: -0.0000

Data Index: 1640520 (Python Code)

Max Activating Token Index: 243

Text #14

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.6599. Min Act: -0.0000

Data Index: 1569120 (Python Code)

Max Activating Token Index: 83

Text #15

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.6786. Min Act: -0.0000

Data Index: 1482352 (Python Code)

Max Activating Token Index: 87

Text #16

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.6340. Min Act: -0.0000

Data Index: 1458100 (Python Code)

Max Activating Token Index: 273

Text #17

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1530590 (Python Code)

Max Activating Token Index: 784

Text #18

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.6454. Min Act: -0.0000

Data Index: 1523077 (Python Code)

Max Activating Token Index: 59

Text #19

Max Range: 0.9987. Min Range: -0.9987

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1654528 (Python Code)

Max Activating Token Index: 58