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

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

Neuron 5159 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.6612. Min Act: -0.0000

Data Index: 1380723 (Python Code)

Max Activating Token Index: 519

Text #1

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.9653. Min Act: -0.0000

Data Index: 1438990 (Python Code)

Max Activating Token Index: 916

Text #2

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.6746. Min Act: -0.0000

Data Index: 1650606 (Python Code)

Max Activating Token Index: 638

Text #3

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.6609. Min Act: -0.0000

Data Index: 1638103 (Python Code)

Max Activating Token Index: 794

Text #4

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.6525. Min Act: -0.0000

Data Index: 1464693 (Python Code)

Max Activating Token Index: 773

Text #5

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.6459. Min Act: -0.0000

Data Index: 1552121 (Python Code)

Max Activating Token Index: 721

Text #6

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.6813. Min Act: -0.0000

Data Index: 1387784 (Python Code)

Max Activating Token Index: 292

Text #7

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.8317. Min Act: -0.0000

Data Index: 1635218 (Python Code)

Max Activating Token Index: 855

Text #8

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.7200. Min Act: -0.0000

Data Index: 1372885 (Python Code)

Max Activating Token Index: 626

Text #9

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.5564. Min Act: -0.0000

Data Index: 1610563 (Python Code)

Max Activating Token Index: 850

Text #10

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.3754. Min Act: -0.0000

Data Index: 1453129 (Python Code)

Max Activating Token Index: 603

Text #11

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.3672. Min Act: -0.0000

Data Index: 1387678 (Python Code)

Max Activating Token Index: 837

Text #12

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.5085. Min Act: -0.0000

Data Index: 1544723 (Python Code)

Max Activating Token Index: 560

Text #13

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.3237. Min Act: -0.0000

Data Index: 1408818 (Python Code)

Max Activating Token Index: 755

Text #14

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.4696. Min Act: -0.0000

Data Index: 1536866 (Python Code)

Max Activating Token Index: 280

Text #15

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.3086. Min Act: -0.0000

Data Index: 1586926 (Python Code)

Max Activating Token Index: 895

Text #16

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.3139. Min Act: -0.0000

Data Index: 1612186 (Python Code)

Max Activating Token Index: 319

Text #17

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.3059. Min Act: -0.0000

Data Index: 1606140 (Python Code)

Max Activating Token Index: 462

Text #18

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.4742. Min Act: -0.0000

Data Index: 1553570 (Python Code)

Max Activating Token Index: 32

Text #19

Max Range: 3.9653. Min Range: -3.9653

Max Act: 3.2961. Min Act: -0.0000

Data Index: 1543814 (Python Code)

Max Activating Token Index: 849