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

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

Neuron 3577 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0594. Min Act: -0.0002

Data Index: 193898 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0546. Min Act: -0.0002

Data Index: 150347 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1013795 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1241632 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0512. Min Act: -0.0002

Data Index: 413443 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0473. Min Act: -0.0002

Data Index: 679769 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1320494 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0454. Min Act: -0.0002

Data Index: 798133 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1248363 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0359. Min Act: -0.0002

Data Index: 132563 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0479. Min Act: -0.0002

Data Index: 574063 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0426. Min Act: -0.0002

Data Index: 201503 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0417. Min Act: -0.0002

Data Index: 788289 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0498. Min Act: -0.0002

Data Index: 949066 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0526. Min Act: -0.0002

Data Index: 317651 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0437. Min Act: -0.0002

Data Index: 425761 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0504. Min Act: -0.0002

Data Index: 754887 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1104075 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0428. Min Act: -0.0002

Data Index: 634089 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1212033 (C4 (Web Text))

Max Activating Token Index: 1018