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

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

Neuron 3804 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.3423. Min Act: -0.0001

Data Index: 1021287 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.3248. Min Act: -0.0001

Data Index: 1017911 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.2031. Min Act: -0.0001

Data Index: 379394 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.2180. Min Act: -0.0001

Data Index: 282620 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.2458. Min Act: -0.0001

Data Index: 340592 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.1642. Min Act: -0.0001

Data Index: 148800 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.2189. Min Act: -0.0001

Data Index: 518016 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.1318. Min Act: -0.0001

Data Index: 785688 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.1832. Min Act: -0.0001

Data Index: 337743 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.1770. Min Act: -0.0001

Data Index: 28958 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.1144. Min Act: -0.0001

Data Index: 760381 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.0711. Min Act: -0.0001

Data Index: 1162526 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.1322. Min Act: -0.0001

Data Index: 494923 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.0909. Min Act: -0.0001

Data Index: 529233 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.0820. Min Act: -0.0001

Data Index: 418622 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.0516. Min Act: -0.0001

Data Index: 987636 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.0676. Min Act: -0.0001

Data Index: 762208 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.0423. Min Act: -0.0001

Data Index: 1072364 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 1.3423. Min Range: -1.3423

Max Act: 1.0711. Min Act: -0.0001

Data Index: 102234 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 1.3423. Min Range: -1.3423

Max Act: 0.9686. Min Act: -0.0001

Data Index: 1026449 (C4 (Web Text))

Max Activating Token Index: 572