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

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

Neuron 1445 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0755. Min Act: -0.0000

Data Index: 20053 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0729. Min Act: -0.0000

Data Index: 1354119 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0706. Min Act: -0.0000

Data Index: 1561934 (Python Code)

Max Activating Token Index: 998

Text #3

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0659. Min Act: -0.0000

Data Index: 1060290 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0663. Min Act: -0.0000

Data Index: 1303215 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0662. Min Act: -0.0000

Data Index: 646943 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0657. Min Act: -0.0000

Data Index: 1227177 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0611. Min Act: -0.0000

Data Index: 535343 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0630. Min Act: -0.0000

Data Index: 1294468 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0626. Min Act: -0.0000

Data Index: 1047523 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0616. Min Act: -0.0000

Data Index: 682875 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0607. Min Act: -0.0000

Data Index: 1037352 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0569. Min Act: -0.0000

Data Index: 1211159 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0610. Min Act: -0.0000

Data Index: 19895 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0625. Min Act: -0.0000

Data Index: 1001203 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0658. Min Act: -0.0000

Data Index: 1308869 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0546. Min Act: -0.0000

Data Index: 744863 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0536. Min Act: -0.0000

Data Index: 150178 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0553. Min Act: -0.0000

Data Index: 337076 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.0755. Min Range: -0.0755

Max Act: 0.0575. Min Act: -0.0000

Data Index: 312040 (C4 (Web Text))

Max Activating Token Index: 653