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

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

Neuron 4243 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.5871. Min Act: -0.0000

Data Index: 1050660 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4813. Min Act: -0.0000

Data Index: 766664 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4066. Min Act: -0.0000

Data Index: 1402478 (Python Code)

Max Activating Token Index: 755

Text #3

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1088509 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4433. Min Act: -0.0000

Data Index: 649074 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3863. Min Act: -0.0000

Data Index: 197710 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4009. Min Act: -0.0000

Data Index: 1418017 (Python Code)

Max Activating Token Index: 463

Text #7

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1438214 (Python Code)

Max Activating Token Index: 500

Text #8

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3730. Min Act: -0.0000

Data Index: 234541 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3546. Min Act: -0.0000

Data Index: 1262710 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3394. Min Act: 0.0000

Data Index: 181884 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3927. Min Act: -0.0000

Data Index: 916063 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3453. Min Act: -0.0000

Data Index: 288325 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3093. Min Act: -0.0000

Data Index: 1525976 (Python Code)

Max Activating Token Index: 42

Text #14

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3055. Min Act: -0.0000

Data Index: 888829 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3150. Min Act: -0.0000

Data Index: 1350983 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3017. Min Act: -0.0000

Data Index: 1151707 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3107. Min Act: -0.0000

Data Index: 1634923 (Python Code)

Max Activating Token Index: 263

Text #18

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3154. Min Act: -0.0000

Data Index: 254612 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.3322. Min Act: -0.0000

Data Index: 986186 (C4 (Web Text))

Max Activating Token Index: 257