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

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

Neuron 1328 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: 0.0742. Min Range: -0.0742

Max Act: 0.0718. Min Act: -0.0004

Data Index: 927580 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0658. Min Act: -0.0004

Data Index: 1065390 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0719. Min Act: -0.0004

Data Index: 72224 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0668. Min Act: -0.0004

Data Index: 398656 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0612. Min Act: -0.0004

Data Index: 19102 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0664. Min Act: -0.0004

Data Index: 210453 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0605. Min Act: -0.0004

Data Index: 1096100 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0685. Min Act: -0.0004

Data Index: 824724 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0605. Min Act: -0.0004

Data Index: 432969 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0676. Min Act: -0.0004

Data Index: 497718 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0615. Min Act: -0.0004

Data Index: 641993 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0742. Min Act: -0.0004

Data Index: 350709 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0607. Min Act: -0.0004

Data Index: 343180 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0606. Min Act: -0.0004

Data Index: 203936 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0510. Min Act: -0.0004

Data Index: 513304 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0658. Min Act: -0.0004

Data Index: 118571 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0656. Min Act: -0.0004

Data Index: 716280 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0578. Min Act: -0.0004

Data Index: 114597 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0598. Min Act: -0.0004

Data Index: 266811 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0593. Min Act: -0.0004

Data Index: 1353541 (C4 (Web Text))

Max Activating Token Index: 307