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

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

Neuron 1745 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.5688. Min Act: -0.0000

Data Index: 45200 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.5065. Min Act: -0.0000

Data Index: 475802 (C4 (Web Text))

Max Activating Token Index: 499

Text #2

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.4563. Min Act: -0.0000

Data Index: 1301239 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.4938. Min Act: -0.0000

Data Index: 1366856 (Python Code)

Max Activating Token Index: 145

Text #4

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.4375. Min Act: -0.0000

Data Index: 1246759 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.4913. Min Act: -0.0000

Data Index: 1056330 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.5175. Min Act: -0.0000

Data Index: 1249413 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.4150. Min Act: -0.0000

Data Index: 29486 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.5212. Min Act: -0.0000

Data Index: 524857 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.4731. Min Act: -0.0000

Data Index: 884974 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.3431. Min Act: -0.0000

Data Index: 513451 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.3832. Min Act: -0.0000

Data Index: 403492 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.3783. Min Act: -0.0000

Data Index: 217627 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.3819. Min Act: -0.0000

Data Index: 1495181 (Python Code)

Max Activating Token Index: 672

Text #14

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.4827. Min Act: -0.0000

Data Index: 1577432 (Python Code)

Max Activating Token Index: 114

Text #15

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.3526. Min Act: -0.0000

Data Index: 1338206 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.3615. Min Act: -0.0000

Data Index: 369664 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.3737. Min Act: -0.0000

Data Index: 484932 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.3700. Min Act: -0.0000

Data Index: 540150 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.4687. Min Act: -0.0000

Data Index: 39731 (C4 (Web Text))

Max Activating Token Index: 209