Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1243 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0813. Min Act: -0.0004

Data Index: 175954 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0687. Min Act: -0.0004

Data Index: 1312964 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0690. Min Act: -0.0004

Data Index: 992824 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0655. Min Act: -0.0004

Data Index: 27800 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0607. Min Act: -0.0004

Data Index: 614216 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0634. Min Act: -0.0004

Data Index: 1068913 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0627. Min Act: -0.0004

Data Index: 209365 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0601. Min Act: -0.0004

Data Index: 511917 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0595. Min Act: -0.0004

Data Index: 845397 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0615. Min Act: -0.0004

Data Index: 734441 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0587. Min Act: -0.0004

Data Index: 851793 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0604. Min Act: -0.0004

Data Index: 897422 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0611. Min Act: -0.0004

Data Index: 1109355 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0628. Min Act: -0.0004

Data Index: 1006876 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0629. Min Act: -0.0004

Data Index: 908827 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0552. Min Act: -0.0004

Data Index: 718778 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0597. Min Act: -0.0004

Data Index: 626924 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0624. Min Act: -0.0004

Data Index: 533440 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0586. Min Act: -0.0004

Data Index: 474602 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0456. Min Act: -0.0004

Data Index: 1140589 (C4 (Web Text))

Max Activating Token Index: 344