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

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

Neuron 1489 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: 0.1748. Min Range: -0.1748

Max Act: 0.1748. Min Act: -0.0002

Data Index: 66566 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1736. Min Act: -0.0002

Data Index: 949251 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1660. Min Act: -0.0002

Data Index: 20755 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1639. Min Act: -0.0002

Data Index: 225433 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1597. Min Act: -0.0002

Data Index: 605457 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1600. Min Act: -0.0002

Data Index: 598827 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1508. Min Act: -0.0002

Data Index: 1260792 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1530. Min Act: -0.0002

Data Index: 1183713 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1402. Min Act: -0.0002

Data Index: 348756 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1380. Min Act: -0.0002

Data Index: 1202677 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1386. Min Act: -0.0002

Data Index: 455666 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1413. Min Act: -0.0002

Data Index: 1022603 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1357. Min Act: -0.0002

Data Index: 391312 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1394. Min Act: -0.0002

Data Index: 236622 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1389. Min Act: -0.0002

Data Index: 72252 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1375. Min Act: -0.0002

Data Index: 138176 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1297. Min Act: -0.0002

Data Index: 483338 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1398. Min Act: -0.0002

Data Index: 670407 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1380. Min Act: -0.0002

Data Index: 16127 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1392. Min Act: -0.0002

Data Index: 984194 (C4 (Web Text))

Max Activating Token Index: 771