Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1124 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0540. Min Range: -1.0540

Max Act: 1.0330. Min Act: -0.0001

Data Index: 1171342 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 1.0540. Min Range: -1.0540

Max Act: 1.0540. Min Act: -0.0001

Data Index: 356883 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9338. Min Act: -0.0001

Data Index: 1219957 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9639. Min Act: -0.0001

Data Index: 297070 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9241. Min Act: -0.0001

Data Index: 784007 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9643. Min Act: -0.0001

Data Index: 571012 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9130. Min Act: -0.0001

Data Index: 267113 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9031. Min Act: -0.0001

Data Index: 1297180 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9536. Min Act: -0.0001

Data Index: 553656 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8525. Min Act: -0.0001

Data Index: 979737 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9326. Min Act: -0.0001

Data Index: 696414 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8716. Min Act: -0.0001

Data Index: 367147 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8693. Min Act: -0.0001

Data Index: 870850 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9110. Min Act: -0.0001

Data Index: 342535 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8263. Min Act: -0.0001

Data Index: 1003660 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8502. Min Act: -0.0001

Data Index: 452041 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8086. Min Act: -0.0001

Data Index: 503616 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8585. Min Act: -0.0001

Data Index: 693977 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8190. Min Act: -0.0001

Data Index: 408039 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8121. Min Act: -0.0001

Data Index: 1090081 (C4 (Web Text))

Max Activating Token Index: 877