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

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

Neuron 4138 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1718. Min Act: -0.0003

Data Index: 669483 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1747. Min Act: -0.0003

Data Index: 594611 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1577. Min Act: -0.0003

Data Index: 102026 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1622. Min Act: -0.0003

Data Index: 653955 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1566. Min Act: -0.0003

Data Index: 270696 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1622. Min Act: -0.0003

Data Index: 157311 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1610. Min Act: -0.0003

Data Index: 848127 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1548. Min Act: -0.0003

Data Index: 455680 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1598. Min Act: -0.0003

Data Index: 1253124 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1535. Min Act: -0.0003

Data Index: 287946 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1575. Min Act: -0.0003

Data Index: 536314 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1570. Min Act: -0.0003

Data Index: 777411 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1424. Min Act: -0.0003

Data Index: 960152 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1530. Min Act: -0.0003

Data Index: 173796 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1454. Min Act: -0.0003

Data Index: 1323745 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1567. Min Act: -0.0003

Data Index: 95449 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1443. Min Act: -0.0003

Data Index: 426799 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1483. Min Act: -0.0003

Data Index: 797654 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1486. Min Act: -0.0003

Data Index: 1181506 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1410. Min Act: -0.0002

Data Index: 226522 (C4 (Web Text))

Max Activating Token Index: 715