Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1147 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0771. Min Act: -0.0001

Data Index: 758491 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0748. Min Act: -0.0002

Data Index: 501104 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0699. Min Act: -0.0002

Data Index: 835902 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1049127 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0692. Min Act: -0.0002

Data Index: 454525 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0685. Min Act: -0.0002

Data Index: 642715 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0669. Min Act: -0.0002

Data Index: 845573 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0664. Min Act: -0.0001

Data Index: 966230 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0637. Min Act: -0.0002

Data Index: 499170 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0641. Min Act: -0.0002

Data Index: 885643 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0614. Min Act: -0.0002

Data Index: 504597 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0629. Min Act: -0.0001

Data Index: 1183614 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0624. Min Act: -0.0002

Data Index: 976712 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1158486 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0623. Min Act: -0.0001

Data Index: 28465 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0616. Min Act: -0.0002

Data Index: 110711 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0597. Min Act: -0.0002

Data Index: 649270 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0609. Min Act: -0.0002

Data Index: 595423 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0611. Min Act: -0.0002

Data Index: 10365 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0602. Min Act: -0.0001

Data Index: 763029 (C4 (Web Text))

Max Activating Token Index: 200