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

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

Neuron 1267 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.6340. Min Act: -0.0000

Data Index: 250584 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.7736. Min Act: -0.0001

Data Index: 1313141 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.6070. Min Act: -0.0001

Data Index: 696987 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.5967. Min Act: -0.0001

Data Index: 491077 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.6914. Min Act: -0.0001

Data Index: 643093 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.6378. Min Act: -0.0001

Data Index: 1036061 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.4744. Min Act: -0.0001

Data Index: 972216 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.2928. Min Act: -0.0000

Data Index: 1031879 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.6046. Min Act: -0.0000

Data Index: 353029 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.3361. Min Act: -0.0001

Data Index: 544218 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.4817. Min Act: -0.0001

Data Index: 506254 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.3175. Min Act: -0.0001

Data Index: 467647 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.1445. Min Act: -0.0001

Data Index: 240798 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.2716. Min Act: -0.0000

Data Index: 281515 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.4680. Min Act: -0.0000

Data Index: 1038504 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.2789. Min Act: -0.0000

Data Index: 683197 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.1354. Min Act: -0.0001

Data Index: 1309722 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.1393. Min Act: -0.0000

Data Index: 937620 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 4.7736. Min Range: -4.7736

Max Act: 3.9722. Min Act: -0.0001

Data Index: 429015 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.1062. Min Act: -0.0000

Data Index: 1331597 (C4 (Web Text))

Max Activating Token Index: 512