Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 738 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1130494 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0436. Min Act: -0.0002

Data Index: 576009 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0376. Min Act: -0.0002

Data Index: 835255 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0391. Min Act: -0.0002

Data Index: 32833 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0361. Min Act: -0.0002

Data Index: 271978 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0386. Min Act: -0.0002

Data Index: 92610 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0363. Min Act: -0.0002

Data Index: 281260 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1355852 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0338. Min Act: -0.0002

Data Index: 244233 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0357. Min Act: -0.0002

Data Index: 32559 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0343. Min Act: -0.0002

Data Index: 961135 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0343. Min Act: -0.0002

Data Index: 179945 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1316514 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0348. Min Act: -0.0002

Data Index: 547602 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0345. Min Act: -0.0002

Data Index: 1236554 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1082483 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0337. Min Act: -0.0002

Data Index: 543514 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0339. Min Act: -0.0002

Data Index: 811909 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0341. Min Act: -0.0002

Data Index: 646880 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0339. Min Act: -0.0002

Data Index: 504167 (C4 (Web Text))

Max Activating Token Index: 347