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

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

Neuron 704 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: 0.0453. Min Range: -0.0453

Max Act: 0.0453. Min Act: -0.0006

Data Index: 511578 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0412. Min Act: -0.0006

Data Index: 266267 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0409. Min Act: -0.0006

Data Index: 1084108 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0405. Min Act: -0.0006

Data Index: 808954 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0420. Min Act: -0.0006

Data Index: 14691 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0413. Min Act: -0.0006

Data Index: 635012 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0401. Min Act: -0.0006

Data Index: 657811 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0414. Min Act: -0.0006

Data Index: 268607 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0419. Min Act: -0.0006

Data Index: 422505 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0405. Min Act: -0.0006

Data Index: 1175653 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0387. Min Act: -0.0006

Data Index: 500979 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0422. Min Act: -0.0006

Data Index: 973628 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0404. Min Act: -0.0006

Data Index: 41900 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0406. Min Act: -0.0006

Data Index: 34941 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0391. Min Act: -0.0006

Data Index: 206468 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0390. Min Act: -0.0006

Data Index: 1270174 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0388. Min Act: -0.0006

Data Index: 813254 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0394. Min Act: -0.0006

Data Index: 325125 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0393. Min Act: -0.0006

Data Index: 1057612 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0379. Min Act: -0.0006

Data Index: 966579 (C4 (Web Text))

Max Activating Token Index: 510