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

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

Neuron 4486 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: 4.8578. Min Range: -4.8578

Max Act: 4.8578. Min Act: -0.0000

Data Index: 1010647 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 4.8578. Min Range: -4.8578

Max Act: 3.9134. Min Act: -0.0000

Data Index: 229106 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 4.8578. Min Range: -4.8578

Max Act: 3.6032. Min Act: -0.0000

Data Index: 164380 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 4.8578. Min Range: -4.8578

Max Act: 3.4543. Min Act: -0.0000

Data Index: 1253862 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 4.8578. Min Range: -4.8578

Max Act: 3.2819. Min Act: -0.0000

Data Index: 112852 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 4.8578. Min Range: -4.8578

Max Act: 3.2586. Min Act: -0.0000

Data Index: 902334 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 4.8578. Min Range: -4.8578

Max Act: 3.3019. Min Act: -0.0000

Data Index: 163287 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 4.8578. Min Range: -4.8578

Max Act: 3.1312. Min Act: -0.0000

Data Index: 840687 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 4.8578. Min Range: -4.8578

Max Act: 3.2121. Min Act: -0.0000

Data Index: 314970 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 4.8578. Min Range: -4.8578

Max Act: 2.9279. Min Act: -0.0000

Data Index: 1190480 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 4.8578. Min Range: -4.8578

Max Act: 3.0502. Min Act: -0.0000

Data Index: 1344626 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 4.8578. Min Range: -4.8578

Max Act: 3.0025. Min Act: -0.0000

Data Index: 6608 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 4.8578. Min Range: -4.8578

Max Act: 2.7495. Min Act: -0.0000

Data Index: 94075 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 4.8578. Min Range: -4.8578

Max Act: 2.8571. Min Act: -0.0000

Data Index: 1048338 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 4.8578. Min Range: -4.8578

Max Act: 2.7613. Min Act: -0.0000

Data Index: 776733 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 4.8578. Min Range: -4.8578

Max Act: 2.8678. Min Act: -0.0000

Data Index: 678443 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 4.8578. Min Range: -4.8578

Max Act: 2.7009. Min Act: -0.0000

Data Index: 1117078 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 4.8578. Min Range: -4.8578

Max Act: 2.9087. Min Act: -0.0000

Data Index: 840265 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 4.8578. Min Range: -4.8578

Max Act: 2.8746. Min Act: -0.0000

Data Index: 1011173 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 4.8578. Min Range: -4.8578

Max Act: 2.6113. Min Act: -0.0000

Data Index: 366606 (C4 (Web Text))

Max Activating Token Index: 769