Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 165 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1609042 (Python Code)

Max Activating Token Index: 1000

Text #1

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0501. Min Act: -0.0003

Data Index: 1286180 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0508. Min Act: -0.0004

Data Index: 185046 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0484. Min Act: -0.0003

Data Index: 351829 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1197601 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0422. Min Act: -0.0003

Data Index: 303805 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0436. Min Act: -0.0003

Data Index: 275608 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0423. Min Act: -0.0003

Data Index: 701115 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0436. Min Act: -0.0003

Data Index: 149455 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0431. Min Act: -0.0003

Data Index: 1371322 (Python Code)

Max Activating Token Index: 952

Text #10

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0429. Min Act: -0.0003

Data Index: 81505 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1268553 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0396. Min Act: -0.0003

Data Index: 385909 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0409. Min Act: -0.0003

Data Index: 1115245 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0428. Min Act: -0.0003

Data Index: 869235 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0411. Min Act: -0.0002

Data Index: 289975 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0388. Min Act: -0.0003

Data Index: 368775 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1239520 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0380. Min Act: -0.0003

Data Index: 769119 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0395. Min Act: -0.0002

Data Index: 647676 (C4 (Web Text))

Max Activating Token Index: 965