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

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

Neuron 858 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: 0.0423. Min Range: -0.0423

Max Act: 0.0423. Min Act: -0.0005

Data Index: 17781 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0403. Min Act: -0.0005

Data Index: 875171 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0408. Min Act: -0.0005

Data Index: 647589 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0400. Min Act: -0.0005

Data Index: 363530 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0404. Min Act: -0.0005

Data Index: 413444 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0396. Min Act: -0.0005

Data Index: 72174 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0393. Min Act: -0.0005

Data Index: 183976 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0405. Min Act: -0.0005

Data Index: 512899 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0398. Min Act: -0.0005

Data Index: 1005474 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0389. Min Act: -0.0005

Data Index: 684313 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0398. Min Act: -0.0005

Data Index: 1163472 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0396. Min Act: -0.0005

Data Index: 592323 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0385. Min Act: -0.0005

Data Index: 1206230 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0387. Min Act: -0.0005

Data Index: 154873 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0378. Min Act: -0.0005

Data Index: 28651 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0392. Min Act: -0.0005

Data Index: 489359 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0389. Min Act: -0.0005

Data Index: 1013651 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0387. Min Act: -0.0005

Data Index: 860887 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0370. Min Act: -0.0005

Data Index: 344716 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0369. Min Act: -0.0005

Data Index: 129025 (C4 (Web Text))

Max Activating Token Index: 350