Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1652 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0479. Min Act: -0.0006

Data Index: 569798 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0496. Min Act: -0.0006

Data Index: 1014324 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0472. Min Act: -0.0006

Data Index: 988115 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0431. Min Act: -0.0006

Data Index: 1152046 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0440. Min Act: -0.0006

Data Index: 900938 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0442. Min Act: -0.0006

Data Index: 397996 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0438. Min Act: -0.0006

Data Index: 385615 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0399. Min Act: -0.0006

Data Index: 1115770 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0411. Min Act: -0.0006

Data Index: 1150116 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0459. Min Act: -0.0006

Data Index: 1237234 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0423. Min Act: -0.0006

Data Index: 340573 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0398. Min Act: -0.0006

Data Index: 146189 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0418. Min Act: -0.0006

Data Index: 1013052 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0383. Min Act: -0.0006

Data Index: 1006014 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0390. Min Act: -0.0006

Data Index: 1134509 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0413. Min Act: -0.0006

Data Index: 446281 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0430. Min Act: -0.0006

Data Index: 397203 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0386. Min Act: -0.0006

Data Index: 370135 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0402. Min Act: -0.0006

Data Index: 779458 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0384. Min Act: -0.0006

Data Index: 738179 (C4 (Web Text))

Max Activating Token Index: 437