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

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

Neuron 398 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: 0.8731. Min Range: -0.8731

Max Act: 0.8731. Min Act: -0.0000

Data Index: 100627 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7614. Min Act: -0.0000

Data Index: 960570 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7379. Min Act: -0.0000

Data Index: 859986 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7156. Min Act: -0.0000

Data Index: 160693 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7616. Min Act: -0.0000

Data Index: 1265659 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6639. Min Act: -0.0000

Data Index: 698841 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.5920. Min Act: -0.0000

Data Index: 426655 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1130957 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.4999. Min Act: -0.0000

Data Index: 103113 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1114964 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.5020. Min Act: -0.0000

Data Index: 1288628 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.5682. Min Act: -0.0000

Data Index: 353265 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.5104. Min Act: -0.0000

Data Index: 1222960 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1170318 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1645174 (Python Code)

Max Activating Token Index: 984

Text #15

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.4589. Min Act: -0.0000

Data Index: 641158 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1639534 (Python Code)

Max Activating Token Index: 508

Text #17

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1073120 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.4399. Min Act: -0.0000

Data Index: 662961 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.4159. Min Act: -0.0000

Data Index: 1644822 (Python Code)

Max Activating Token Index: 874