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

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

Neuron 1595 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0275. Min Range: -1.0275

Max Act: 1.0275. Min Act: -0.0003

Data Index: 449560 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 1.0275. Min Range: -1.0275

Max Act: 0.9625. Min Act: -0.0003

Data Index: 503331 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 1.0275. Min Range: -1.0275

Max Act: 0.9258. Min Act: -0.0003

Data Index: 527479 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 1.0275. Min Range: -1.0275

Max Act: 0.8207. Min Act: -0.0003

Data Index: 431878 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 1.0275. Min Range: -1.0275

Max Act: 0.8337. Min Act: -0.0003

Data Index: 556039 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 1.0275. Min Range: -1.0275

Max Act: 0.7918. Min Act: -0.0003

Data Index: 1239403 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 1.0275. Min Range: -1.0275

Max Act: 0.8051. Min Act: -0.0003

Data Index: 342065 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 1.0275. Min Range: -1.0275

Max Act: 0.7784. Min Act: -0.0003

Data Index: 1241307 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 1.0275. Min Range: -1.0275

Max Act: 0.7766. Min Act: -0.0003

Data Index: 179197 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 1.0275. Min Range: -1.0275

Max Act: 0.8028. Min Act: -0.0003

Data Index: 236953 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 1.0275. Min Range: -1.0275

Max Act: 0.8062. Min Act: -0.0002

Data Index: 1135351 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 1.0275. Min Range: -1.0275

Max Act: 0.7720. Min Act: -0.0003

Data Index: 914639 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 1.0275. Min Range: -1.0275

Max Act: 0.7356. Min Act: -0.0003

Data Index: 237672 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 1.0275. Min Range: -1.0275

Max Act: 0.7833. Min Act: -0.0003

Data Index: 1315841 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 1.0275. Min Range: -1.0275

Max Act: 0.7575. Min Act: -0.0002

Data Index: 1280291 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 1.0275. Min Range: -1.0275

Max Act: 0.7704. Min Act: -0.0003

Data Index: 860050 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 1.0275. Min Range: -1.0275

Max Act: 0.7892. Min Act: -0.0003

Data Index: 825111 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 1.0275. Min Range: -1.0275

Max Act: 0.7331. Min Act: -0.0003

Data Index: 529885 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.0275. Min Range: -1.0275

Max Act: 0.7388. Min Act: -0.0003

Data Index: 1154879 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 1.0275. Min Range: -1.0275

Max Act: 0.7599. Min Act: -0.0003

Data Index: 463347 (C4 (Web Text))

Max Activating Token Index: 600