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

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

Neuron 492 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: 0.0529. Min Range: -0.0529

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1196619 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0474. Min Act: -0.0002

Data Index: 688956 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1358679 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0451. Min Act: -0.0002

Data Index: 354520 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0441. Min Act: -0.0002

Data Index: 78825 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0421. Min Act: -0.0002

Data Index: 672748 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0434. Min Act: -0.0002

Data Index: 92330 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0423. Min Act: -0.0002

Data Index: 699562 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1180993 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1181113 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0426. Min Act: -0.0002

Data Index: 640765 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1058980 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0415. Min Act: -0.0002

Data Index: 27785 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1170759 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0419. Min Act: -0.0002

Data Index: 243725 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1267507 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0411. Min Act: -0.0002

Data Index: 903304 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0403. Min Act: -0.0002

Data Index: 791529 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0375. Min Act: -0.0002

Data Index: 703060 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1287275 (C4 (Web Text))

Max Activating Token Index: 605