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

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

Neuron 5045 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1295703 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.2152. Min Act: -0.0000

Data Index: 1104326 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.2284. Min Act: -0.0000

Data Index: 397711 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1798. Min Act: -0.0000

Data Index: 835318 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1876. Min Act: -0.0000

Data Index: 908732 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1830. Min Act: -0.0000

Data Index: 65455 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1733. Min Act: -0.0000

Data Index: 761748 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1682. Min Act: -0.0000

Data Index: 333680 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1611. Min Act: -0.0000

Data Index: 1034574 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1536. Min Act: -0.0000

Data Index: 1340477 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1453. Min Act: -0.0000

Data Index: 944013 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1716. Min Act: -0.0000

Data Index: 750533 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1573. Min Act: -0.0000

Data Index: 1221977 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1689. Min Act: -0.0000

Data Index: 1325808 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1575. Min Act: -0.0000

Data Index: 972201 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1573. Min Act: -0.0000

Data Index: 691764 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1440. Min Act: -0.0000

Data Index: 354598 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1572. Min Act: -0.0000

Data Index: 408220 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1553. Min Act: -0.0000

Data Index: 1292708 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1456. Min Act: -0.0000

Data Index: 923388 (C4 (Web Text))

Max Activating Token Index: 203