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

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

Neuron 5600 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4441. Min Range: -2.4441

Max Act: 2.3532. Min Act: -0.0000

Data Index: 42561 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 2.4441. Min Range: -2.4441

Max Act: 2.4441. Min Act: -0.0000

Data Index: 892006 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 2.4441. Min Range: -2.4441

Max Act: 2.3626. Min Act: -0.0000

Data Index: 1014933 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 2.4441. Min Range: -2.4441

Max Act: 2.1629. Min Act: -0.0000

Data Index: 396871 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 2.4441. Min Range: -2.4441

Max Act: 2.1455. Min Act: 0.0000

Data Index: 996973 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 2.4441. Min Range: -2.4441

Max Act: 1.9687. Min Act: -0.0000

Data Index: 530750 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 2.4441. Min Range: -2.4441

Max Act: 2.0831. Min Act: -0.0000

Data Index: 849422 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 2.4441. Min Range: -2.4441

Max Act: 2.0735. Min Act: -0.0000

Data Index: 230690 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 2.4441. Min Range: -2.4441

Max Act: 2.0513. Min Act: -0.0000

Data Index: 503203 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 2.4441. Min Range: -2.4441

Max Act: 1.8716. Min Act: -0.0000

Data Index: 991510 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 2.4441. Min Range: -2.4441

Max Act: 1.9841. Min Act: 0.0001

Data Index: 514648 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 2.4441. Min Range: -2.4441

Max Act: 1.9720. Min Act: -0.0000

Data Index: 934077 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 2.4441. Min Range: -2.4441

Max Act: 1.8407. Min Act: -0.0000

Data Index: 989393 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 2.4441. Min Range: -2.4441

Max Act: 2.0349. Min Act: -0.0000

Data Index: 14767 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 2.4441. Min Range: -2.4441

Max Act: 1.9767. Min Act: -0.0000

Data Index: 740145 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 2.4441. Min Range: -2.4441

Max Act: 1.8598. Min Act: -0.0000

Data Index: 965838 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 2.4441. Min Range: -2.4441

Max Act: 1.8599. Min Act: -0.0000

Data Index: 1096595 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 2.4441. Min Range: -2.4441

Max Act: 1.8438. Min Act: -0.0000

Data Index: 891960 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 2.4441. Min Range: -2.4441

Max Act: 1.8071. Min Act: -0.0000

Data Index: 1155134 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 2.4441. Min Range: -2.4441

Max Act: 1.8020. Min Act: -0.0000

Data Index: 239636 (C4 (Web Text))

Max Activating Token Index: 1007