Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3989 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9641. Min Range: -2.9641

Max Act: 2.9641. Min Act: -0.0000

Data Index: 1443143 (Python Code)

Max Activating Token Index: 461

Text #1

Max Range: 2.9641. Min Range: -2.9641

Max Act: 2.8458. Min Act: -0.0000

Data Index: 1604036 (Python Code)

Max Activating Token Index: 955

Text #2

Max Range: 2.9641. Min Range: -2.9641

Max Act: 2.8568. Min Act: -0.0000

Data Index: 1611628 (Python Code)

Max Activating Token Index: 683

Text #3

Max Range: 2.9641. Min Range: -2.9641

Max Act: 2.6051. Min Act: -0.0000

Data Index: 1409252 (Python Code)

Max Activating Token Index: 403

Text #4

Max Range: 2.9641. Min Range: -2.9641

Max Act: 2.7217. Min Act: -0.0000

Data Index: 234129 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 2.9641. Min Range: -2.9641

Max Act: 2.6785. Min Act: -0.0000

Data Index: 1646642 (Python Code)

Max Activating Token Index: 608

Text #6

Max Range: 2.9641. Min Range: -2.9641

Max Act: 2.6791. Min Act: -0.0000

Data Index: 92896 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 2.9641. Min Range: -2.9641

Max Act: 2.6689. Min Act: -0.0000

Data Index: 1426662 (Python Code)

Max Activating Token Index: 505

Text #8

Max Range: 2.9641. Min Range: -2.9641

Max Act: 2.5905. Min Act: -0.0000

Data Index: 1623907 (Python Code)

Max Activating Token Index: 622

Text #9

Max Range: 2.9641. Min Range: -2.9641

Max Act: 2.5969. Min Act: -0.0000

Data Index: 1431994 (Python Code)

Max Activating Token Index: 773

Text #10

Max Range: 2.9641. Min Range: -2.9641

Max Act: 2.4792. Min Act: -0.0000

Data Index: 1445506 (Python Code)

Max Activating Token Index: 712

Text #11

Max Range: 2.9641. Min Range: -2.9641

Max Act: 2.6771. Min Act: -0.0000

Data Index: 1529150 (Python Code)

Max Activating Token Index: 335

Text #12

Max Range: 2.9641. Min Range: -2.9641

Max Act: 2.5503. Min Act: -0.0000

Data Index: 1516786 (Python Code)

Max Activating Token Index: 261

Text #13

Max Range: 2.9641. Min Range: -2.9641

Max Act: 2.5484. Min Act: -0.0000

Data Index: 1616672 (Python Code)

Max Activating Token Index: 301

Text #14

Max Range: 2.9641. Min Range: -2.9641

Max Act: 2.6429. Min Act: -0.0000

Data Index: 1640406 (Python Code)

Max Activating Token Index: 520

Text #15

Max Range: 2.9641. Min Range: -2.9641

Max Act: 2.3461. Min Act: -0.0000

Data Index: 1365682 (Python Code)

Max Activating Token Index: 823

Text #16

Max Range: 2.9641. Min Range: -2.9641

Max Act: 2.3353. Min Act: -0.0000

Data Index: 1522228 (Python Code)

Max Activating Token Index: 737

Text #17

Max Range: 2.9641. Min Range: -2.9641

Max Act: 2.4396. Min Act: -0.0000

Data Index: 1539763 (Python Code)

Max Activating Token Index: 641

Text #18

Max Range: 2.9641. Min Range: -2.9641

Max Act: 2.5321. Min Act: -0.0000

Data Index: 1560088 (Python Code)

Max Activating Token Index: 97

Text #19

Max Range: 2.9641. Min Range: -2.9641

Max Act: 2.3829. Min Act: -0.0000

Data Index: 1647275 (Python Code)

Max Activating Token Index: 968