Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3133 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.7194. Min Act: -0.0000

Data Index: 1015151 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.7010. Min Act: -0.0000

Data Index: 374471 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.4256. Min Act: -0.0000

Data Index: 687321 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.3992. Min Act: -0.0000

Data Index: 664599 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.3914. Min Act: -0.0000

Data Index: 511202 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.3873. Min Act: -0.0000

Data Index: 546904 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.4356. Min Act: -0.0000

Data Index: 341811 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.3939. Min Act: -0.0000

Data Index: 366572 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.3772. Min Act: -0.0000

Data Index: 1648321 (Python Code)

Max Activating Token Index: 762

Text #9

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1478086 (Python Code)

Max Activating Token Index: 620

Text #10

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.3780. Min Act: -0.0000

Data Index: 1553032 (Python Code)

Max Activating Token Index: 876

Text #11

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.3667. Min Act: -0.0000

Data Index: 1454400 (Python Code)

Max Activating Token Index: 824

Text #12

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.3535. Min Act: -0.0000

Data Index: 1513039 (Python Code)

Max Activating Token Index: 653

Text #13

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.3765. Min Act: -0.0000

Data Index: 1517262 (Python Code)

Max Activating Token Index: 526

Text #14

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.3594. Min Act: -0.0000

Data Index: 159107 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.3490. Min Act: -0.0000

Data Index: 71729 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.3605. Min Act: -0.0000

Data Index: 1433267 (Python Code)

Max Activating Token Index: 560

Text #17

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.3585. Min Act: -0.0000

Data Index: 1441337 (Python Code)

Max Activating Token Index: 379

Text #18

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.3773. Min Act: -0.0000

Data Index: 1528652 (Python Code)

Max Activating Token Index: 565

Text #19

Max Range: 0.7194. Min Range: -0.7194

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1441837 (Python Code)

Max Activating Token Index: 877