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

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

Neuron 2007 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: 1.0974. Min Range: -1.0974

Max Act: 1.0974. Min Act: -0.0000

Data Index: 892982 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.9838. Min Act: -0.0000

Data Index: 269392 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.9422. Min Act: -0.0000

Data Index: 896557 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.9320. Min Act: -0.0001

Data Index: 796275 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.9042. Min Act: -0.0001

Data Index: 1074094 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.9060. Min Act: -0.0000

Data Index: 1068807 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.9248. Min Act: -0.0000

Data Index: 427905 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.9157. Min Act: -0.0000

Data Index: 310049 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.9076. Min Act: -0.0000

Data Index: 753601 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8874. Min Act: -0.0000

Data Index: 609949 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8285. Min Act: -0.0000

Data Index: 349210 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8496. Min Act: -0.0001

Data Index: 584041 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1273880 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8937. Min Act: -0.0000

Data Index: 1323535 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8654. Min Act: -0.0000

Data Index: 1574408 (Python Code)

Max Activating Token Index: 981

Text #15

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8381. Min Act: -0.0000

Data Index: 713449 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8601. Min Act: -0.0000

Data Index: 997720 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1409456 (Python Code)

Max Activating Token Index: 797

Text #18

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8549. Min Act: -0.0000

Data Index: 361022 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1389156 (Python Code)

Max Activating Token Index: 478