Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1938 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0764. Min Act: -0.0003

Data Index: 134247 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0807. Min Act: -0.0003

Data Index: 1035510 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0706. Min Act: -0.0004

Data Index: 1356233 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0770. Min Act: -0.0003

Data Index: 1325893 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0690. Min Act: -0.0003

Data Index: 919894 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0666. Min Act: -0.0003

Data Index: 923155 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0688. Min Act: -0.0003

Data Index: 96648 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0683. Min Act: -0.0003

Data Index: 449126 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0662. Min Act: -0.0003

Data Index: 171498 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0671. Min Act: -0.0003

Data Index: 192938 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0706. Min Act: -0.0003

Data Index: 12661 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0667. Min Act: -0.0003

Data Index: 436746 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0694. Min Act: -0.0003

Data Index: 320129 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0666. Min Act: -0.0003

Data Index: 620607 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0641. Min Act: -0.0003

Data Index: 629290 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0660. Min Act: -0.0003

Data Index: 319073 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0601. Min Act: -0.0003

Data Index: 1132296 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0640. Min Act: -0.0003

Data Index: 169381 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0622. Min Act: -0.0004

Data Index: 1104852 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0681. Min Act: -0.0003

Data Index: 515148 (C4 (Web Text))

Max Activating Token Index: 1015