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

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

Neuron 3101 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.9651. Min Act: -0.0000

Data Index: 596308 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.8709. Min Act: 0.0001

Data Index: 1603834 (Python Code)

Max Activating Token Index: 165

Text #2

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.8550. Min Act: -0.0000

Data Index: 416860 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7698. Min Act: -0.0000

Data Index: 384401 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7425. Min Act: -0.0000

Data Index: 815755 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.7678. Min Act: -0.0000

Data Index: 736110 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.6972. Min Act: -0.0000

Data Index: 1019706 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.6798. Min Act: 0.0002

Data Index: 1490413 (Python Code)

Max Activating Token Index: 219

Text #8

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.6526. Min Act: 0.0002

Data Index: 1607845 (Python Code)

Max Activating Token Index: 115

Text #9

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.6413. Min Act: -0.0000

Data Index: 806075 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1374058 (Python Code)

Max Activating Token Index: 734

Text #11

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.5901. Min Act: -0.0000

Data Index: 418964 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.5701. Min Act: -0.0000

Data Index: 851921 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.5740. Min Act: 0.0000

Data Index: 939251 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1640299 (Python Code)

Max Activating Token Index: 818

Text #15

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.5493. Min Act: 0.0001

Data Index: 1390507 (Python Code)

Max Activating Token Index: 180

Text #16

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.5603. Min Act: -0.0000

Data Index: 295778 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.5443. Min Act: 0.0002

Data Index: 1393836 (Python Code)

Max Activating Token Index: 406

Text #18

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.5579. Min Act: -0.0000

Data Index: 160507 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.9651. Min Range: -0.9651

Max Act: 0.5371. Min Act: -0.0000

Data Index: 1066011 (C4 (Web Text))

Max Activating Token Index: 92