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

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

Neuron 4319 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: 1.5656. Min Range: -1.5656

Max Act: 1.5656. Min Act: -0.0000

Data Index: 921094 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.3697. Min Act: -0.0000

Data Index: 41129 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.2703. Min Act: -0.0000

Data Index: 33849 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.3976. Min Act: -0.0000

Data Index: 703474 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.3021. Min Act: -0.0000

Data Index: 1148262 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.3632. Min Act: -0.0000

Data Index: 1006761 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.2701. Min Act: -0.0000

Data Index: 1276137 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.2387. Min Act: -0.0000

Data Index: 179720 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.2343. Min Act: -0.0000

Data Index: 497156 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.2279. Min Act: -0.0000

Data Index: 843699 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.2275. Min Act: -0.0000

Data Index: 325916 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.2532. Min Act: -0.0000

Data Index: 334778 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.1716. Min Act: -0.0000

Data Index: 1171208 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.2099. Min Act: -0.0001

Data Index: 20690 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.1891. Min Act: -0.0000

Data Index: 994092 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.2552. Min Act: -0.0000

Data Index: 646684 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.1791. Min Act: -0.0000

Data Index: 786550 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.1511. Min Act: -0.0000

Data Index: 690654 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.2207. Min Act: -0.0000

Data Index: 529569 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 1.5656. Min Range: -1.5656

Max Act: 1.1409. Min Act: -0.0000

Data Index: 216470 (C4 (Web Text))

Max Activating Token Index: 667