Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1698 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2599. Min Act: -0.0001

Data Index: 978507 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2410. Min Act: -0.0001

Data Index: 494551 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2514. Min Act: -0.0001

Data Index: 885932 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2394. Min Act: -0.0001

Data Index: 671027 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2673. Min Act: -0.0001

Data Index: 595622 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2438. Min Act: -0.0001

Data Index: 1243924 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2396. Min Act: -0.0001

Data Index: 602072 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2460. Min Act: -0.0001

Data Index: 754552 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2344. Min Act: -0.0001

Data Index: 897394 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2611. Min Act: -0.0001

Data Index: 1115952 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2411. Min Act: -0.0001

Data Index: 941693 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2455. Min Act: -0.0001

Data Index: 634079 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2399. Min Act: -0.0001

Data Index: 1227002 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2473. Min Act: -0.0001

Data Index: 941732 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2412. Min Act: -0.0001

Data Index: 1281589 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2418. Min Act: -0.0001

Data Index: 574007 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2306. Min Act: -0.0001

Data Index: 974614 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2340. Min Act: -0.0001

Data Index: 165333 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2426. Min Act: -0.0001

Data Index: 1047837 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.2673. Min Range: -0.2673

Max Act: 0.2410. Min Act: -0.0001

Data Index: 817816 (C4 (Web Text))

Max Activating Token Index: 289