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

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

Neuron 3457 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: 1.0881. Min Range: -1.0881

Max Act: 1.0881. Min Act: 0.0000

Data Index: 779992 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 1.0881. Min Range: -1.0881

Max Act: 1.0481. Min Act: 0.0001

Data Index: 296876 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 1.0881. Min Range: -1.0881

Max Act: 1.0412. Min Act: -0.0000

Data Index: 829707 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 1.0881. Min Range: -1.0881

Max Act: 1.0186. Min Act: -0.0000

Data Index: 350415 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 1.0881. Min Range: -1.0881

Max Act: 1.0332. Min Act: -0.0000

Data Index: 954559 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 1.0881. Min Range: -1.0881

Max Act: 1.0275. Min Act: 0.0000

Data Index: 68099 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.9938. Min Act: 0.0000

Data Index: 537760 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.9819. Min Act: -0.0000

Data Index: 199300 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 1.0881. Min Range: -1.0881

Max Act: 1.0341. Min Act: -0.0000

Data Index: 792069 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.9898. Min Act: -0.0000

Data Index: 42418 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.9438. Min Act: -0.0000

Data Index: 1134686 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.8774. Min Act: -0.0000

Data Index: 41454 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.8983. Min Act: -0.0000

Data Index: 759775 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.9560. Min Act: -0.0000

Data Index: 1234729 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.9450. Min Act: -0.0000

Data Index: 243711 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.8804. Min Act: 0.0001

Data Index: 488927 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.9248. Min Act: -0.0000

Data Index: 308796 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.9183. Min Act: -0.0000

Data Index: 1339917 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.8472. Min Act: -0.0000

Data Index: 1232692 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.8357. Min Act: -0.0000

Data Index: 210468 (C4 (Web Text))

Max Activating Token Index: 606