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

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

Neuron 1656 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1584. Min Act: -0.0001

Data Index: 887294 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1591. Min Act: -0.0001

Data Index: 939043 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1645. Min Act: -0.0001

Data Index: 1268190 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1536. Min Act: -0.0001

Data Index: 1294297 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1578. Min Act: -0.0001

Data Index: 521558 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1747. Min Act: -0.0001

Data Index: 519068 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1517. Min Act: -0.0001

Data Index: 696021 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1578. Min Act: -0.0000

Data Index: 501103 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1570. Min Act: -0.0000

Data Index: 321867 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1522. Min Act: -0.0001

Data Index: 1145805 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1451. Min Act: -0.0001

Data Index: 1118962 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1623. Min Act: -0.0001

Data Index: 473123 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1571. Min Act: -0.0001

Data Index: 675024 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1597. Min Act: -0.0000

Data Index: 1042174 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1593. Min Act: -0.0001

Data Index: 576611 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1495. Min Act: -0.0001

Data Index: 597740 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1623. Min Act: -0.0001

Data Index: 633319 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1588. Min Act: -0.0001

Data Index: 1147965 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1427. Min Act: -0.0000

Data Index: 239359 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1533. Min Act: -0.0001

Data Index: 467904 (C4 (Web Text))

Max Activating Token Index: 568