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

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

Neuron 907 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: 0.0785. Min Range: -0.0785

Max Act: 0.0785. Min Act: -0.0004

Data Index: 542775 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0644. Min Act: -0.0003

Data Index: 561846 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0653. Min Act: -0.0003

Data Index: 986261 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0634. Min Act: -0.0003

Data Index: 544403 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0632. Min Act: -0.0003

Data Index: 900456 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0639. Min Act: -0.0003

Data Index: 265011 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0598. Min Act: -0.0003

Data Index: 1345967 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0583. Min Act: -0.0003

Data Index: 1278444 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0593. Min Act: -0.0003

Data Index: 392192 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0572. Min Act: -0.0003

Data Index: 1247285 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0560. Min Act: -0.0004

Data Index: 643118 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0572. Min Act: -0.0003

Data Index: 1171418 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0557. Min Act: -0.0004

Data Index: 1086031 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0573. Min Act: -0.0003

Data Index: 45990 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0560. Min Act: -0.0003

Data Index: 796428 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0547. Min Act: -0.0003

Data Index: 858570 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0530. Min Act: -0.0003

Data Index: 693842 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0544. Min Act: -0.0003

Data Index: 649399 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0544. Min Act: -0.0004

Data Index: 1085219 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0507. Min Act: -0.0003

Data Index: 236906 (C4 (Web Text))

Max Activating Token Index: 957