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

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

Neuron 746 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1095. Min Act: -0.0005

Data Index: 316881 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0529. Min Act: -0.0005

Data Index: 1190749 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0472. Min Act: -0.0005

Data Index: 298697 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0460. Min Act: -0.0005

Data Index: 314295 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0426. Min Act: -0.0005

Data Index: 307240 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0398. Min Act: -0.0005

Data Index: 1003660 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0396. Min Act: -0.0005

Data Index: 232671 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0391. Min Act: -0.0005

Data Index: 773810 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0396. Min Act: -0.0005

Data Index: 277924 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0376. Min Act: -0.0005

Data Index: 1186767 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0392. Min Act: -0.0005

Data Index: 731493 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0364. Min Act: -0.0005

Data Index: 514389 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0359. Min Act: -0.0005

Data Index: 83091 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0375. Min Act: -0.0005

Data Index: 23531 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0336. Min Act: -0.0005

Data Index: 651318 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0320. Min Act: -0.0005

Data Index: 778495 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0351. Min Act: -0.0005

Data Index: 163049 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0350. Min Act: -0.0005

Data Index: 309868 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0333. Min Act: -0.0005

Data Index: 870614 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0326. Min Act: -0.0005

Data Index: 442520 (C4 (Web Text))

Max Activating Token Index: 186