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

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

Neuron 4101 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: 0.6429. Min Range: -0.6429

Max Act: 0.6429. Min Act: -0.0000

Data Index: 768494 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5777. Min Act: -0.0000

Data Index: 728295 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5125. Min Act: -0.0000

Data Index: 1333787 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5339. Min Act: -0.0000

Data Index: 416583 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5262. Min Act: -0.0000

Data Index: 374942 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5313. Min Act: -0.0000

Data Index: 684 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4983. Min Act: -0.0000

Data Index: 669760 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4795. Min Act: -0.0000

Data Index: 1321096 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4659. Min Act: -0.0000

Data Index: 41033 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4453. Min Act: -0.0000

Data Index: 350773 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4667. Min Act: -0.0000

Data Index: 394866 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4635. Min Act: -0.0000

Data Index: 634626 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4418. Min Act: -0.0000

Data Index: 405143 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4662. Min Act: -0.0000

Data Index: 609263 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4337. Min Act: -0.0000

Data Index: 671872 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1020923 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4399. Min Act: -0.0000

Data Index: 260236 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4382. Min Act: -0.0000

Data Index: 762880 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1188580 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4508. Min Act: -0.0000

Data Index: 410965 (C4 (Web Text))

Max Activating Token Index: 388