Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 655 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1790. Min Range: -1.1790

Max Act: 1.1790. Min Act: -0.0000

Data Index: 758451 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 1.1790. Min Range: -1.1790

Max Act: 1.1690. Min Act: -0.0000

Data Index: 11709 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 1.1790. Min Range: -1.1790

Max Act: 1.0910. Min Act: -0.0000

Data Index: 523133 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 1.1790. Min Range: -1.1790

Max Act: 1.0526. Min Act: -0.0000

Data Index: 872562 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 1.1790. Min Range: -1.1790

Max Act: 0.9301. Min Act: -0.0000

Data Index: 987805 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 1.1790. Min Range: -1.1790

Max Act: 0.9706. Min Act: -0.0000

Data Index: 711243 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 1.1790. Min Range: -1.1790

Max Act: 0.9724. Min Act: -0.0000

Data Index: 711080 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 1.1790. Min Range: -1.1790

Max Act: 0.9917. Min Act: -0.0000

Data Index: 945547 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 1.1790. Min Range: -1.1790

Max Act: 0.9150. Min Act: -0.0000

Data Index: 500601 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 1.1790. Min Range: -1.1790

Max Act: 0.9575. Min Act: -0.0000

Data Index: 110103 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 1.1790. Min Range: -1.1790

Max Act: 0.9660. Min Act: -0.0000

Data Index: 62507 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 1.1790. Min Range: -1.1790

Max Act: 0.9111. Min Act: -0.0000

Data Index: 1002441 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 1.1790. Min Range: -1.1790

Max Act: 0.8790. Min Act: -0.0000

Data Index: 39350 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 1.1790. Min Range: -1.1790

Max Act: 0.8983. Min Act: -0.0000

Data Index: 274689 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 1.1790. Min Range: -1.1790

Max Act: 0.8727. Min Act: -0.0000

Data Index: 1043740 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 1.1790. Min Range: -1.1790

Max Act: 0.8978. Min Act: -0.0000

Data Index: 552491 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 1.1790. Min Range: -1.1790

Max Act: 0.8495. Min Act: -0.0000

Data Index: 1243796 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 1.1790. Min Range: -1.1790

Max Act: 0.8465. Min Act: -0.0000

Data Index: 1067608 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 1.1790. Min Range: -1.1790

Max Act: 0.8740. Min Act: -0.0000

Data Index: 599394 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 1.1790. Min Range: -1.1790

Max Act: 0.8655. Min Act: -0.0000

Data Index: 403998 (C4 (Web Text))

Max Activating Token Index: 522