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

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

Neuron 563 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: 0.0704. Min Range: -0.0704

Max Act: 0.0704. Min Act: -0.0003

Data Index: 205801 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0694. Min Act: -0.0003

Data Index: 255327 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0685. Min Act: -0.0002

Data Index: 557740 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0678. Min Act: -0.0003

Data Index: 245201 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0673. Min Act: -0.0004

Data Index: 411981 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0674. Min Act: -0.0003

Data Index: 205180 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0681. Min Act: -0.0003

Data Index: 724090 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0689. Min Act: -0.0004

Data Index: 948692 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0666. Min Act: -0.0003

Data Index: 25256 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0664. Min Act: -0.0003

Data Index: 1187700 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0656. Min Act: -0.0004

Data Index: 521992 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0643. Min Act: -0.0003

Data Index: 79046 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0645. Min Act: -0.0003

Data Index: 490719 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0622. Min Act: -0.0003

Data Index: 281573 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0651. Min Act: -0.0002

Data Index: 1010844 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0631. Min Act: -0.0003

Data Index: 1131410 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0622. Min Act: -0.0003

Data Index: 43242 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0630. Min Act: -0.0003

Data Index: 584552 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0620. Min Act: -0.0003

Data Index: 1296200 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0608. Min Act: -0.0003

Data Index: 970702 (C4 (Web Text))

Max Activating Token Index: 640