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

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

Neuron 4486 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3323. Min Act: -0.0002

Data Index: 8394 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2824. Min Act: -0.0002

Data Index: 1075271 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2834. Min Act: -0.0002

Data Index: 269652 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2783. Min Act: -0.0002

Data Index: 771213 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2591. Min Act: -0.0002

Data Index: 782609 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2646. Min Act: -0.0002

Data Index: 211813 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2493. Min Act: -0.0002

Data Index: 1217073 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2502. Min Act: -0.0002

Data Index: 997967 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2556. Min Act: -0.0002

Data Index: 685569 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2614. Min Act: -0.0002

Data Index: 1353695 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2499. Min Act: -0.0002

Data Index: 6326 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2602. Min Act: -0.0002

Data Index: 461710 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2479. Min Act: -0.0002

Data Index: 724438 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2464. Min Act: -0.0002

Data Index: 1178443 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2644. Min Act: -0.0002

Data Index: 1266290 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2377. Min Act: -0.0002

Data Index: 255507 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2366. Min Act: -0.0002

Data Index: 1246372 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2420. Min Act: -0.0002

Data Index: 982676 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2410. Min Act: -0.0002

Data Index: 823984 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2343. Min Act: -0.0002

Data Index: 1088624 (C4 (Web Text))

Max Activating Token Index: 903