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

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

Neuron 3314 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0369. Min Act: -0.0001

Data Index: 1616310 (Python Code)

Max Activating Token Index: 787

Text #1

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0283. Min Act: -0.0001

Data Index: 1648650 (Python Code)

Max Activating Token Index: 476

Text #2

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0283. Min Act: -0.0001

Data Index: 1591846 (Python Code)

Max Activating Token Index: 207

Text #3

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0284. Min Act: -0.0001

Data Index: 1387905 (Python Code)

Max Activating Token Index: 674

Text #4

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0276. Min Act: -0.0001

Data Index: 531795 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0292. Min Act: -0.0002

Data Index: 83177 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1059560 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0263. Min Act: -0.0001

Data Index: 1527168 (Python Code)

Max Activating Token Index: 808

Text #8

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0253. Min Act: -0.0001

Data Index: 1396805 (Python Code)

Max Activating Token Index: 911

Text #9

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0249. Min Act: -0.0001

Data Index: 921142 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0236. Min Act: -0.0001

Data Index: 1590028 (Python Code)

Max Activating Token Index: 473

Text #11

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0244. Min Act: -0.0001

Data Index: 1492254 (Python Code)

Max Activating Token Index: 817

Text #12

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0257. Min Act: -0.0001

Data Index: 1233151 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0219. Min Act: -0.0001

Data Index: 1413968 (Python Code)

Max Activating Token Index: 583

Text #14

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0229. Min Act: -0.0001

Data Index: 1596543 (Python Code)

Max Activating Token Index: 395

Text #15

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0214. Min Act: -0.0001

Data Index: 1479233 (Python Code)

Max Activating Token Index: 886

Text #16

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0246. Min Act: -0.0001

Data Index: 1405771 (Python Code)

Max Activating Token Index: 576

Text #17

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0227. Min Act: -0.0001

Data Index: 1370423 (Python Code)

Max Activating Token Index: 935

Text #18

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0241. Min Act: -0.0001

Data Index: 1421264 (Python Code)

Max Activating Token Index: 194

Text #19

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1381785 (Python Code)

Max Activating Token Index: 532