Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1417 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0723. Min Act: -0.0003

Data Index: 729933 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0576. Min Act: -0.0003

Data Index: 419088 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0557. Min Act: -0.0003

Data Index: 116973 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0555. Min Act: -0.0003

Data Index: 1134470 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0502. Min Act: -0.0003

Data Index: 776224 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0508. Min Act: -0.0003

Data Index: 1355014 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0527. Min Act: -0.0003

Data Index: 1350597 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0544. Min Act: -0.0003

Data Index: 713555 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0526. Min Act: -0.0003

Data Index: 537544 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1073477 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0490. Min Act: -0.0003

Data Index: 569699 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0472. Min Act: -0.0003

Data Index: 916343 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0467. Min Act: -0.0003

Data Index: 215436 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0505. Min Act: -0.0003

Data Index: 598243 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0503. Min Act: -0.0003

Data Index: 845467 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0497. Min Act: -0.0003

Data Index: 729166 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0514. Min Act: -0.0003

Data Index: 1240122 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0492. Min Act: -0.0003

Data Index: 798318 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0511. Min Act: -0.0003

Data Index: 211383 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1039962 (C4 (Web Text))

Max Activating Token Index: 950