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

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

Neuron 500 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0749. Min Act: -0.0005

Data Index: 351322 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0750. Min Act: -0.0005

Data Index: 513791 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0735. Min Act: -0.0005

Data Index: 1016491 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0685. Min Act: -0.0005

Data Index: 814559 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0691. Min Act: -0.0005

Data Index: 424029 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0658. Min Act: -0.0005

Data Index: 661736 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0656. Min Act: -0.0005

Data Index: 489350 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0706. Min Act: -0.0005

Data Index: 1271822 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0646. Min Act: -0.0005

Data Index: 201576 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0648. Min Act: -0.0005

Data Index: 1201028 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0600. Min Act: -0.0005

Data Index: 1293257 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0604. Min Act: -0.0005

Data Index: 1123896 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0655. Min Act: -0.0005

Data Index: 564502 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0617. Min Act: -0.0005

Data Index: 758560 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0626. Min Act: -0.0005

Data Index: 1265170 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0608. Min Act: -0.0005

Data Index: 40778 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0596. Min Act: -0.0005

Data Index: 1110107 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0571. Min Act: -0.0005

Data Index: 1263373 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0563. Min Act: -0.0005

Data Index: 27224 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0580. Min Act: -0.0005

Data Index: 716731 (C4 (Web Text))

Max Activating Token Index: 699