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

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

Neuron 1793 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0186. Min Range: -1.0186

Max Act: 1.0186. Min Act: -0.0000

Data Index: 413420 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 1.0186. Min Range: -1.0186

Max Act: 0.8432. Min Act: -0.0000

Data Index: 676753 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 1.0186. Min Range: -1.0186

Max Act: 0.7321. Min Act: -0.0000

Data Index: 624866 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 1.0186. Min Range: -1.0186

Max Act: 0.8299. Min Act: -0.0000

Data Index: 909690 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 1.0186. Min Range: -1.0186

Max Act: 0.7891. Min Act: -0.0000

Data Index: 589341 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 1.0186. Min Range: -1.0186

Max Act: 0.7963. Min Act: -0.0000

Data Index: 699808 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 1.0186. Min Range: -1.0186

Max Act: 0.6986. Min Act: -0.0000

Data Index: 155641 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 1.0186. Min Range: -1.0186

Max Act: 0.6730. Min Act: -0.0000

Data Index: 150923 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 1.0186. Min Range: -1.0186

Max Act: 0.6784. Min Act: -0.0000

Data Index: 588580 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 1.0186. Min Range: -1.0186

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1060869 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 1.0186. Min Range: -1.0186

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1121111 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 1.0186. Min Range: -1.0186

Max Act: 0.6349. Min Act: -0.0000

Data Index: 742820 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 1.0186. Min Range: -1.0186

Max Act: 0.6406. Min Act: -0.0000

Data Index: 1237850 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 1.0186. Min Range: -1.0186

Max Act: 0.6760. Min Act: -0.0000

Data Index: 845678 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 1.0186. Min Range: -1.0186

Max Act: 0.6633. Min Act: -0.0000

Data Index: 39699 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 1.0186. Min Range: -1.0186

Max Act: 0.6019. Min Act: -0.0000

Data Index: 607928 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 1.0186. Min Range: -1.0186

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1017249 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 1.0186. Min Range: -1.0186

Max Act: 0.6059. Min Act: -0.0000

Data Index: 849094 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 1.0186. Min Range: -1.0186

Max Act: 0.5767. Min Act: -0.0000

Data Index: 71638 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 1.0186. Min Range: -1.0186

Max Act: 0.6105. Min Act: -0.0000

Data Index: 985888 (C4 (Web Text))

Max Activating Token Index: 724