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

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

Neuron 2225 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8957. Min Range: -6.8957

Max Act: 6.8696. Min Act: -0.0000

Data Index: 962075 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 6.8957. Min Range: -6.8957

Max Act: 6.5402. Min Act: -0.0000

Data Index: 92895 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 6.8957. Min Range: -6.8957

Max Act: 6.8957. Min Act: -0.0000

Data Index: 840422 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 6.8957. Min Range: -6.8957

Max Act: 6.4772. Min Act: -0.0000

Data Index: 909758 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 6.8957. Min Range: -6.8957

Max Act: 6.3883. Min Act: -0.0000

Data Index: 861945 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 6.8957. Min Range: -6.8957

Max Act: 5.7476. Min Act: -0.0000

Data Index: 16391 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 6.8957. Min Range: -6.8957

Max Act: 5.9552. Min Act: -0.0000

Data Index: 1051191 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 6.8957. Min Range: -6.8957

Max Act: 6.0965. Min Act: -0.0000

Data Index: 1028918 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 6.8957. Min Range: -6.8957

Max Act: 6.4586. Min Act: -0.0000

Data Index: 194030 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 6.8957. Min Range: -6.8957

Max Act: 6.7281. Min Act: -0.0000

Data Index: 1283715 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 6.8957. Min Range: -6.8957

Max Act: 6.2977. Min Act: -0.0000

Data Index: 206754 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 6.8957. Min Range: -6.8957

Max Act: 5.7861. Min Act: -0.0000

Data Index: 172738 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 6.8957. Min Range: -6.8957

Max Act: 5.8197. Min Act: -0.0000

Data Index: 196645 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 6.8957. Min Range: -6.8957

Max Act: 5.8848. Min Act: -0.0000

Data Index: 1267215 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 6.8957. Min Range: -6.8957

Max Act: 5.8078. Min Act: -0.0000

Data Index: 747162 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 6.8957. Min Range: -6.8957

Max Act: 5.5806. Min Act: -0.0000

Data Index: 576928 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 6.8957. Min Range: -6.8957

Max Act: 5.9758. Min Act: -0.0000

Data Index: 993071 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 6.8957. Min Range: -6.8957

Max Act: 6.1024. Min Act: -0.0000

Data Index: 600264 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 6.8957. Min Range: -6.8957

Max Act: 5.6759. Min Act: -0.0000

Data Index: 1077569 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 6.8957. Min Range: -6.8957

Max Act: 5.7766. Min Act: -0.0000

Data Index: 590098 (C4 (Web Text))

Max Activating Token Index: 589