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

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

Neuron 5469 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9981. Min Range: -0.9981

Max Act: 0.9981. Min Act: -0.0000

Data Index: 793896 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.9981. Min Range: -0.9981

Max Act: 0.9827. Min Act: -0.0000

Data Index: 223786 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.9981. Min Range: -0.9981

Max Act: 0.7947. Min Act: -0.0000

Data Index: 636308 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.9981. Min Range: -0.9981

Max Act: 0.7718. Min Act: -0.0000

Data Index: 986102 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.9981. Min Range: -0.9981

Max Act: 0.6905. Min Act: -0.0000

Data Index: 354168 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 0.9981. Min Range: -0.9981

Max Act: 0.7423. Min Act: -0.0000

Data Index: 567994 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.9981. Min Range: -0.9981

Max Act: 0.6932. Min Act: -0.0000

Data Index: 684275 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.9981. Min Range: -0.9981

Max Act: 0.6910. Min Act: -0.0000

Data Index: 1032843 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.9981. Min Range: -0.9981

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1029188 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.9981. Min Range: -0.9981

Max Act: 0.6964. Min Act: -0.0000

Data Index: 604580 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.9981. Min Range: -0.9981

Max Act: 0.7043. Min Act: -0.0000

Data Index: 271437 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 0.9981. Min Range: -0.9981

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1081792 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.9981. Min Range: -0.9981

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1567746 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 0.9981. Min Range: -0.9981

Max Act: 0.6607. Min Act: -0.0000

Data Index: 256272 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.9981. Min Range: -0.9981

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1043871 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.9981. Min Range: -0.9981

Max Act: 0.6484. Min Act: -0.0000

Data Index: 727691 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 0.9981. Min Range: -0.9981

Max Act: 0.6530. Min Act: -0.0000

Data Index: 921541 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.9981. Min Range: -0.9981

Max Act: 0.6493. Min Act: -0.0000

Data Index: 57359 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.9981. Min Range: -0.9981

Max Act: 0.6215. Min Act: -0.0000

Data Index: 783935 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.9981. Min Range: -0.9981

Max Act: 0.6351. Min Act: -0.0000

Data Index: 431834 (C4 (Web Text))

Max Activating Token Index: 583