Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 631 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0802. Min Act: -0.0003

Data Index: 586288 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0766. Min Act: -0.0003

Data Index: 422065 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0792. Min Act: -0.0003

Data Index: 1124570 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0731. Min Act: -0.0003

Data Index: 449550 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0701. Min Act: -0.0003

Data Index: 1034213 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0719. Min Act: -0.0003

Data Index: 1342084 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0701. Min Act: -0.0003

Data Index: 707837 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0691. Min Act: -0.0003

Data Index: 156728 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0668. Min Act: -0.0003

Data Index: 37728 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0643. Min Act: -0.0003

Data Index: 928034 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0641. Min Act: -0.0003

Data Index: 342392 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0655. Min Act: -0.0003

Data Index: 249627 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0666. Min Act: -0.0003

Data Index: 1151951 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0637. Min Act: -0.0003

Data Index: 81465 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0668. Min Act: -0.0003

Data Index: 774698 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0665. Min Act: -0.0003

Data Index: 672268 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0652. Min Act: -0.0003

Data Index: 348516 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0588. Min Act: -0.0003

Data Index: 814129 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0636. Min Act: -0.0003

Data Index: 194080 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0663. Min Act: -0.0003

Data Index: 512391 (C4 (Web Text))

Max Activating Token Index: 852