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

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

Neuron 4494 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.9345. Min Act: -0.0000

Data Index: 351946 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 3.0641. Min Range: -3.0641

Max Act: 3.0641. Min Act: -0.0000

Data Index: 1137175 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.8671. Min Act: -0.0000

Data Index: 372815 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.6718. Min Act: -0.0000

Data Index: 939701 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.5816. Min Act: -0.0000

Data Index: 1191499 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.5178. Min Act: -0.0000

Data Index: 1273344 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.5276. Min Act: -0.0000

Data Index: 623000 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.4368. Min Act: -0.0000

Data Index: 974245 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.4209. Min Act: -0.0000

Data Index: 584499 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.3557. Min Act: -0.0000

Data Index: 621258 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.1891. Min Act: -0.0000

Data Index: 1081373 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.2421. Min Act: -0.0000

Data Index: 1158595 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.1419. Min Act: -0.0000

Data Index: 607611 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.1276. Min Act: -0.0000

Data Index: 203406 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.0758. Min Act: -0.0000

Data Index: 680249 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 3.0641. Min Range: -3.0641

Max Act: 1.9603. Min Act: -0.0000

Data Index: 734036 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.2965. Min Act: -0.0000

Data Index: 53880 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 3.0641. Min Range: -3.0641

Max Act: 2.0539. Min Act: -0.0000

Data Index: 1617425 (Python Code)

Max Activating Token Index: 528

Text #18

Max Range: 3.0641. Min Range: -3.0641

Max Act: 1.9744. Min Act: -0.0000

Data Index: 979992 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 3.0641. Min Range: -3.0641

Max Act: 1.8719. Min Act: -0.0000

Data Index: 827198 (C4 (Web Text))

Max Activating Token Index: 270