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

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

Neuron 1865 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1398. Min Act: -0.0006

Data Index: 303667 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1434. Min Act: -0.0006

Data Index: 365352 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1241. Min Act: -0.0006

Data Index: 1308336 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1456. Min Act: -0.0006

Data Index: 220119 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1247. Min Act: -0.0006

Data Index: 685655 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1245. Min Act: -0.0006

Data Index: 1024123 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1251. Min Act: -0.0006

Data Index: 1153537 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1245. Min Act: -0.0006

Data Index: 749449 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1350. Min Act: -0.0006

Data Index: 1322902 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1288. Min Act: -0.0006

Data Index: 1217463 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1284. Min Act: -0.0006

Data Index: 918403 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1213. Min Act: -0.0006

Data Index: 562696 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1211. Min Act: -0.0006

Data Index: 764376 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1301. Min Act: -0.0005

Data Index: 328345 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1252. Min Act: -0.0006

Data Index: 125027 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1209. Min Act: -0.0006

Data Index: 1082428 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1199. Min Act: -0.0006

Data Index: 247555 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1299. Min Act: -0.0006

Data Index: 213664 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1200. Min Act: -0.0007

Data Index: 393639 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1392. Min Act: -0.0006

Data Index: 92302 (C4 (Web Text))

Max Activating Token Index: 736