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

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

Neuron 5796 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: 1.0030. Min Range: -1.0030

Max Act: 0.9302. Min Act: -0.0000

Data Index: 287991 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8977. Min Act: -0.0000

Data Index: 226966 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 1.0030. Min Range: -1.0030

Max Act: 1.0030. Min Act: -0.0000

Data Index: 238090 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7123. Min Act: -0.0000

Data Index: 103552 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6635. Min Act: -0.0000

Data Index: 1048527 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6314. Min Act: -0.0000

Data Index: 366548 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6517. Min Act: -0.0000

Data Index: 309898 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1194664 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.5869. Min Act: -0.0000

Data Index: 782456 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.5655. Min Act: -0.0000

Data Index: 21296 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.5866. Min Act: -0.0000

Data Index: 486694 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.5702. Min Act: -0.0000

Data Index: 134975 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1058217 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.5757. Min Act: -0.0000

Data Index: 64966 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.6016. Min Act: -0.0000

Data Index: 196212 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.5725. Min Act: -0.0000

Data Index: 31269 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.4919. Min Act: -0.0000

Data Index: 1110950 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.5147. Min Act: -0.0000

Data Index: 406421 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.5368. Min Act: -0.0000

Data Index: 1097761 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.5467. Min Act: -0.0000

Data Index: 878785 (C4 (Web Text))

Max Activating Token Index: 92