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

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

Neuron 2011 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0479. Min Act: -0.0003

Data Index: 863344 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0486. Min Act: -0.0002

Data Index: 180350 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0480. Min Act: -0.0003

Data Index: 393335 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0452. Min Act: -0.0003

Data Index: 660374 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1006507 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0457. Min Act: -0.0003

Data Index: 1322636 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0422. Min Act: -0.0003

Data Index: 731922 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0440. Min Act: -0.0003

Data Index: 920111 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0409. Min Act: -0.0003

Data Index: 464690 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0413. Min Act: -0.0003

Data Index: 614990 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0399. Min Act: -0.0003

Data Index: 506419 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0394. Min Act: -0.0003

Data Index: 1047828 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0396. Min Act: -0.0003

Data Index: 648683 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0399. Min Act: -0.0003

Data Index: 380949 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1297079 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0398. Min Act: -0.0003

Data Index: 284951 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0394. Min Act: -0.0002

Data Index: 672570 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0386. Min Act: -0.0003

Data Index: 964910 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0381. Min Act: -0.0003

Data Index: 600682 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0395. Min Act: -0.0003

Data Index: 1222387 (C4 (Web Text))

Max Activating Token Index: 312