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

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

Neuron 4028 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.9120. Min Act: -0.0000

Data Index: 242762 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.7288. Min Act: -0.0000

Data Index: 14028 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.6938. Min Act: -0.0000

Data Index: 1123408 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.6254. Min Act: -0.0000

Data Index: 961259 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.6216. Min Act: -0.0000

Data Index: 474315 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5978. Min Act: 0.0000

Data Index: 1050791 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5917. Min Act: -0.0000

Data Index: 846471 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5912. Min Act: -0.0000

Data Index: 306984 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5706. Min Act: -0.0000

Data Index: 322655 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5799. Min Act: -0.0000

Data Index: 257965 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5857. Min Act: -0.0000

Data Index: 453447 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5420. Min Act: -0.0000

Data Index: 324077 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5603. Min Act: -0.0000

Data Index: 1301677 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1527030 (Python Code)

Max Activating Token Index: 81

Text #14

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5486. Min Act: -0.0000

Data Index: 26358 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5446. Min Act: -0.0000

Data Index: 408532 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5611. Min Act: -0.0000

Data Index: 681668 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1393915 (Python Code)

Max Activating Token Index: 965

Text #18

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1640252 (Python Code)

Max Activating Token Index: 76

Text #19

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5648. Min Act: -0.0000

Data Index: 258173 (C4 (Web Text))

Max Activating Token Index: 257