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

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

Neuron 680 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2587. Min Act: -0.0001

Data Index: 298247 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2517. Min Act: -0.0001

Data Index: 1146864 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2551. Min Act: -0.0001

Data Index: 368845 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2369. Min Act: -0.0001

Data Index: 735999 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2359. Min Act: -0.0001

Data Index: 1108880 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2423. Min Act: -0.0001

Data Index: 1035901 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2401. Min Act: -0.0001

Data Index: 704810 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2289. Min Act: -0.0001

Data Index: 605760 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2455. Min Act: -0.0001

Data Index: 138678 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2456. Min Act: -0.0001

Data Index: 648533 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2434. Min Act: -0.0001

Data Index: 733505 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2342. Min Act: -0.0001

Data Index: 1245542 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2266. Min Act: -0.0001

Data Index: 567646 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2336. Min Act: -0.0001

Data Index: 1349062 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2327. Min Act: -0.0001

Data Index: 1234056 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2307. Min Act: -0.0001

Data Index: 325547 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2368. Min Act: -0.0001

Data Index: 412751 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2286. Min Act: -0.0001

Data Index: 397300 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2202. Min Act: -0.0001

Data Index: 1290379 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2192. Min Act: -0.0001

Data Index: 1161553 (C4 (Web Text))

Max Activating Token Index: 494