Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 825 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1260. Min Act: -0.0003

Data Index: 637833 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0749. Min Act: -0.0003

Data Index: 55838 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0648. Min Act: -0.0003

Data Index: 995566 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0532. Min Act: -0.0003

Data Index: 1312020 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0474. Min Act: -0.0003

Data Index: 140090 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0441. Min Act: -0.0003

Data Index: 357166 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0423. Min Act: -0.0003

Data Index: 766533 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0441. Min Act: -0.0003

Data Index: 787047 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0409. Min Act: -0.0003

Data Index: 1140567 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0406. Min Act: -0.0003

Data Index: 851029 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0393. Min Act: -0.0003

Data Index: 621448 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0362. Min Act: -0.0003

Data Index: 498417 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0381. Min Act: -0.0003

Data Index: 502247 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0346. Min Act: -0.0003

Data Index: 1118845 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0378. Min Act: -0.0003

Data Index: 780095 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0329. Min Act: -0.0003

Data Index: 303756 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1309380 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0343. Min Act: -0.0003

Data Index: 807392 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0334. Min Act: -0.0003

Data Index: 826420 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0311. Min Act: -0.0003

Data Index: 301522 (C4 (Web Text))

Max Activating Token Index: 228