Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3310 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0774. Min Act: -0.0003

Data Index: 844401 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0759. Min Act: -0.0003

Data Index: 869641 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0744. Min Act: -0.0003

Data Index: 1113882 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0699. Min Act: -0.0003

Data Index: 524310 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0734. Min Act: -0.0003

Data Index: 738718 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0672. Min Act: -0.0003

Data Index: 1161197 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0666. Min Act: -0.0003

Data Index: 1082 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0684. Min Act: -0.0003

Data Index: 550085 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0678. Min Act: -0.0003

Data Index: 1338908 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0667. Min Act: -0.0003

Data Index: 809556 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0673. Min Act: -0.0003

Data Index: 47505 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0670. Min Act: -0.0004

Data Index: 707550 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0672. Min Act: -0.0003

Data Index: 341397 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0675. Min Act: -0.0003

Data Index: 451857 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0668. Min Act: -0.0004

Data Index: 110103 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0667. Min Act: -0.0003

Data Index: 1034837 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0638. Min Act: -0.0003

Data Index: 684782 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0664. Min Act: -0.0003

Data Index: 71987 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0657. Min Act: -0.0004

Data Index: 56207 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0663. Min Act: -0.0003

Data Index: 187008 (C4 (Web Text))

Max Activating Token Index: 322