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

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

Neuron 1152 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.5589. Min Act: -0.0000

Data Index: 420800 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.5268. Min Act: -0.0000

Data Index: 403507 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3704. Min Act: -0.0000

Data Index: 484824 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3324. Min Act: -0.0000

Data Index: 801946 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1009828 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3196. Min Act: -0.0000

Data Index: 521426 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2969. Min Act: -0.0000

Data Index: 1321391 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2964. Min Act: -0.0000

Data Index: 601363 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2927. Min Act: -0.0000

Data Index: 278804 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2767. Min Act: -0.0000

Data Index: 893822 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2825. Min Act: -0.0000

Data Index: 395830 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2698. Min Act: -0.0000

Data Index: 1236152 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1160197 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2618. Min Act: -0.0000

Data Index: 53904 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2787. Min Act: -0.0000

Data Index: 613447 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2524. Min Act: -0.0000

Data Index: 555091 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2426. Min Act: -0.0000

Data Index: 493065 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1354288 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2564. Min Act: -0.0000

Data Index: 660581 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2545. Min Act: -0.0000

Data Index: 1269609 (C4 (Web Text))

Max Activating Token Index: 668