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

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

Neuron 3634 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8880. Min Range: -4.8880

Max Act: 4.8880. Min Act: -0.0000

Data Index: 381076 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 4.8880. Min Range: -4.8880

Max Act: 4.1876. Min Act: -0.0000

Data Index: 834292 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 4.8880. Min Range: -4.8880

Max Act: 4.3811. Min Act: -0.0000

Data Index: 39003 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 4.8880. Min Range: -4.8880

Max Act: 3.8088. Min Act: -0.0000

Data Index: 734685 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 4.8880. Min Range: -4.8880

Max Act: 3.9211. Min Act: -0.0000

Data Index: 322392 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 4.8880. Min Range: -4.8880

Max Act: 4.0963. Min Act: -0.0000

Data Index: 850714 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 4.8880. Min Range: -4.8880

Max Act: 4.1415. Min Act: -0.0000

Data Index: 618150 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 4.8880. Min Range: -4.8880

Max Act: 3.5855. Min Act: -0.0000

Data Index: 1241547 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 4.8880. Min Range: -4.8880

Max Act: 3.8982. Min Act: -0.0000

Data Index: 945319 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 4.8880. Min Range: -4.8880

Max Act: 3.6908. Min Act: -0.0000

Data Index: 239497 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 4.8880. Min Range: -4.8880

Max Act: 3.6539. Min Act: -0.0000

Data Index: 352983 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 4.8880. Min Range: -4.8880

Max Act: 3.5963. Min Act: -0.0000

Data Index: 1126279 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 4.8880. Min Range: -4.8880

Max Act: 3.5709. Min Act: -0.0000

Data Index: 834412 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 4.8880. Min Range: -4.8880

Max Act: 3.6342. Min Act: -0.0000

Data Index: 106785 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 4.8880. Min Range: -4.8880

Max Act: 3.1526. Min Act: -0.0000

Data Index: 211297 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 4.8880. Min Range: -4.8880

Max Act: 3.6103. Min Act: -0.0000

Data Index: 1214267 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 4.8880. Min Range: -4.8880

Max Act: 3.4491. Min Act: -0.0000

Data Index: 1017584 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 4.8880. Min Range: -4.8880

Max Act: 3.6163. Min Act: -0.0000

Data Index: 230653 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 4.8880. Min Range: -4.8880

Max Act: 3.3058. Min Act: -0.0000

Data Index: 295606 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 4.8880. Min Range: -4.8880

Max Act: 3.4022. Min Act: -0.0000

Data Index: 957526 (C4 (Web Text))

Max Activating Token Index: 694