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

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

Neuron 726 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: 0.0641. Min Range: -0.0641

Max Act: 0.0641. Min Act: -0.0004

Data Index: 398730 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0606. Min Act: -0.0003

Data Index: 995123 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0622. Min Act: -0.0003

Data Index: 574615 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0594. Min Act: -0.0003

Data Index: 1253579 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0599. Min Act: -0.0003

Data Index: 928945 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0592. Min Act: -0.0003

Data Index: 649168 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0580. Min Act: -0.0003

Data Index: 84214 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0576. Min Act: -0.0003

Data Index: 237531 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0571. Min Act: -0.0003

Data Index: 231488 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0561. Min Act: -0.0003

Data Index: 62548 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0585. Min Act: -0.0003

Data Index: 928658 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0556. Min Act: -0.0003

Data Index: 264742 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0544. Min Act: -0.0002

Data Index: 411440 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0562. Min Act: -0.0004

Data Index: 404227 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0537. Min Act: -0.0003

Data Index: 391088 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0583. Min Act: -0.0003

Data Index: 628726 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0532. Min Act: -0.0003

Data Index: 1007543 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0549. Min Act: -0.0003

Data Index: 1214199 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0534. Min Act: -0.0003

Data Index: 377371 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0548. Min Act: -0.0003

Data Index: 1257190 (C4 (Web Text))

Max Activating Token Index: 156