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

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

Neuron 222 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3420. Min Range: -0.3420

Max Act: 0.3336. Min Act: 0.0000

Data Index: 1639062 (Python Code)

Max Activating Token Index: 285

Text #1

Max Range: 0.3420. Min Range: -0.3420

Max Act: 0.3420. Min Act: -0.0000

Data Index: 1360659 (Python Code)

Max Activating Token Index: 713

Text #2

Max Range: 0.3420. Min Range: -0.3420

Max Act: 0.2715. Min Act: -0.0000

Data Index: 616246 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.3420. Min Range: -0.3420

Max Act: 0.2919. Min Act: -0.0000

Data Index: 218700 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.3420. Min Range: -0.3420

Max Act: 0.2956. Min Act: -0.0000

Data Index: 1547694 (Python Code)

Max Activating Token Index: 688

Text #5

Max Range: 0.3420. Min Range: -0.3420

Max Act: 0.2883. Min Act: -0.0000

Data Index: 1357211 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.3420. Min Range: -0.3420

Max Act: 0.2747. Min Act: -0.0000

Data Index: 431818 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.3420. Min Range: -0.3420

Max Act: 0.2722. Min Act: -0.0000

Data Index: 825720 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.3420. Min Range: -0.3420

Max Act: 0.2664. Min Act: -0.0000

Data Index: 401886 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 0.3420. Min Range: -0.3420

Max Act: 0.2671. Min Act: -0.0000

Data Index: 305727 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 0.3420. Min Range: -0.3420

Max Act: 0.2579. Min Act: -0.0000

Data Index: 1535096 (Python Code)

Max Activating Token Index: 662

Text #11

Max Range: 0.3420. Min Range: -0.3420

Max Act: 0.2529. Min Act: -0.0000

Data Index: 898033 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.3420. Min Range: -0.3420

Max Act: 0.2537. Min Act: 0.0000

Data Index: 706258 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.3420. Min Range: -0.3420

Max Act: 0.2343. Min Act: -0.0000

Data Index: 289115 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.3420. Min Range: -0.3420

Max Act: 0.2441. Min Act: -0.0000

Data Index: 1435883 (Python Code)

Max Activating Token Index: 495

Text #15

Max Range: 0.3420. Min Range: -0.3420

Max Act: 0.2429. Min Act: -0.0000

Data Index: 877711 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.3420. Min Range: -0.3420

Max Act: 0.2497. Min Act: -0.0000

Data Index: 1384359 (Python Code)

Max Activating Token Index: 263

Text #17

Max Range: 0.3420. Min Range: -0.3420

Max Act: 0.2645. Min Act: 0.0000

Data Index: 1165804 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.3420. Min Range: -0.3420

Max Act: 0.2438. Min Act: 0.0000

Data Index: 1037012 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.3420. Min Range: -0.3420

Max Act: 0.2482. Min Act: -0.0000

Data Index: 451469 (C4 (Web Text))

Max Activating Token Index: 728