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

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

Neuron 2523 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: 1.1769. Min Range: -1.1769

Max Act: 1.1558. Min Act: -0.0003

Data Index: 379462 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.1769. Min Act: -0.0003

Data Index: 742512 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.0890. Min Act: -0.0003

Data Index: 1095581 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.0984. Min Act: -0.0003

Data Index: 260810 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.0325. Min Act: -0.0003

Data Index: 272778 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9940. Min Act: -0.0003

Data Index: 1103815 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.0222. Min Act: -0.0003

Data Index: 1323085 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9799. Min Act: -0.0003

Data Index: 117151 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.0293. Min Act: -0.0003

Data Index: 910388 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9400. Min Act: -0.0003

Data Index: 1155373 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.0276. Min Act: -0.0003

Data Index: 1163085 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9498. Min Act: -0.0003

Data Index: 708403 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9750. Min Act: -0.0003

Data Index: 882145 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9974. Min Act: -0.0003

Data Index: 1299318 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9425. Min Act: -0.0003

Data Index: 869425 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.8242. Min Act: -0.0003

Data Index: 927419 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.0200. Min Act: -0.0003

Data Index: 464340 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9573. Min Act: -0.0003

Data Index: 571381 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9317. Min Act: -0.0003

Data Index: 1348454 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9819. Min Act: -0.0003

Data Index: 581907 (C4 (Web Text))

Max Activating Token Index: 17