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

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

Neuron 1729 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.2496. Min Act: -0.0001

Data Index: 39917 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.2253. Min Act: -0.0000

Data Index: 125194 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1814. Min Act: -0.0001

Data Index: 1272202 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1261625 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1827. Min Act: -0.0001

Data Index: 198469 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1702. Min Act: -0.0000

Data Index: 1182463 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1731. Min Act: -0.0001

Data Index: 351080 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1633. Min Act: -0.0001

Data Index: 602088 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1632. Min Act: -0.0000

Data Index: 1188456 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1647. Min Act: -0.0001

Data Index: 401407 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1546. Min Act: -0.0001

Data Index: 337413 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1535. Min Act: -0.0001

Data Index: 46593 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1520. Min Act: -0.0001

Data Index: 1035022 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1553. Min Act: -0.0000

Data Index: 554910 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1529. Min Act: -0.0000

Data Index: 818934 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1491. Min Act: -0.0000

Data Index: 478057 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1487. Min Act: -0.0001

Data Index: 656147 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1483. Min Act: -0.0000

Data Index: 634993 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1476. Min Act: -0.0001

Data Index: 1285692 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.2496. Min Range: -0.2496

Max Act: 0.1470. Min Act: -0.0001

Data Index: 648749 (C4 (Web Text))

Max Activating Token Index: 958