Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5578 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.8504. Min Act: -0.0000

Data Index: 505628 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7539. Min Act: -0.0000

Data Index: 392268 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7519. Min Act: -0.0000

Data Index: 1128729 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7442. Min Act: -0.0000

Data Index: 83010 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7316. Min Act: -0.0000

Data Index: 602348 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6410. Min Act: -0.0000

Data Index: 710785 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6303. Min Act: -0.0000

Data Index: 380494 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6421. Min Act: -0.0000

Data Index: 1248191 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1064223 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6264. Min Act: -0.0000

Data Index: 43613 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6000. Min Act: -0.0000

Data Index: 862709 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5982. Min Act: -0.0000

Data Index: 348846 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5587. Min Act: -0.0000

Data Index: 348496 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5748. Min Act: -0.0000

Data Index: 966048 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6289. Min Act: -0.0000

Data Index: 1173368 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5760. Min Act: -0.0000

Data Index: 281703 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5721. Min Act: -0.0000

Data Index: 172913 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6368. Min Act: -0.0000

Data Index: 639591 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5881. Min Act: -0.0000

Data Index: 806896 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5798. Min Act: -0.0000

Data Index: 222895 (C4 (Web Text))

Max Activating Token Index: 87